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

    Neuronpedia

    INDEX
    Explanations

    specific patterns or structures in code and data outputs

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

    sequence of numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     feroit
    -0.59
     indígen
    -0.55
     auroit
    -0.54
     pouvoit
    -0.52
     plufieurs
    -0.47
    onsored
    -0.46
    jenige
    -0.45
     étoit
    -0.42
    ésult
    -0.42
    arangay
    -0.41
    POSITIVE LOGITS
    ########.
    0.51
    qrstuvwxyz
    0.47
    허
    0.46
     pageContext
    0.42
     mu
    0.41
     Administrativna
    0.41
    DockStyle
    0.40
    inc
    0.40
    MeasureSpec
    0.39
    GraphicsUnit
    0.39
    Act Density 0.155%

    No Known Activations