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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ovy
    -0.07
     oversee
    -0.06
    [args
    -0.06
    _-_
    -0.06
    NH
    -0.06
     dripping
    -0.06
    lx
    -0.06
     forgiveness
    -0.06
    кие
    -0.06
    ิโ
    -0.06
    POSITIVE LOGITS
     Lac
    0.07
    Marca
    0.07
     Forbes
    0.06
    -columns
    0.06
    ACHE
    0.06
    zyst
    0.06
     workforce
    0.06
    UIImageView
    0.06
     abb
    0.06
     stressing
    0.06
    Act Density 0.036%

    No Known Activations