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

    Neuronpedia

    INDEX
    Explanations

    and to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     consequently
    -0.09
    isy
    -0.09
    achi
    -0.09
     Collect
    -0.08
    aise
    -0.08
    allery
    -0.08
     UIPickerView
    -0.08
     Garr
    -0.08
    anno
    -0.08
    via
    -0.08
    POSITIVE LOGITS
     να
    0.15
    /or
    0.12
     to
    0.11
     NOT
    0.11
     not
    0.11
     avoid
    0.09
     toReturn
    0.09
    бо
    0.09
     nowhere
    0.09
    éģ¿
    0.09
    Act Density 0.044%

    No Known Activations