Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases indicating agreement or similarity between subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "both" and its context

    np_acts-logits-general · gemini-2.0-flash

    indicating duality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ValueGeneration
    -0.69
    ReusableCell
    -0.68
    WebServlet
    -0.65
    #+#
    -0.64
     AssemblyTitle
    -0.62
    LabelTagHelper
    -0.61
    liosis
    -0.60
    ResumeLayout
    -0.59
    unnitel
    -0.58
    RegressionTest
    -0.58
    POSITIVE LOGITS
     simultaneously
    0.63
     sides
    0.60
     equally
    0.57
     đều
    0.48
     suffer
    0.47
     jeweils
    0.47
     sets
    0.46
     have
    0.44
    Kapcsolódó
    0.44
    StandardCharsets
    0.43
    Act Density 0.276%

    No Known Activations