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

    Neuronpedia

    INDEX
    Explanations

    questions and phrases about methods, processes, and ways to accomplish tasks

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

    "how" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    how to explain

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.76
    SceneManagement
    -0.61
     ::=
    -0.57
     spelling
    -0.53
    ंदीखरीदारी
    -0.52
    getSupport
    -0.51
     meille
    -0.51
    zsche
    -0.50
     להם
    -0.50
    Còn
    -0.50
    POSITIVE LOGITS
     incorporating
    0.58
    principalTable
    0.56
    httphttps
    0.56
     einz
    0.55
     שוליים
    0.54
    openConnection
    0.54
    {}
    0.53
    hawa
    0.53
    ()];
    0.53
    odils
    0.53
    Act Density 0.086%

    No Known Activations