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

    Neuronpedia

    INDEX
    Explanations

    paid parental leave

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     لج
    -0.78
    umbled
    -0.77
     dignidad
    -0.76
    燬
    -0.75
     قیمت
    -0.74
    thenes
    -0.73
    IAH
    -0.73
     CAA
    -0.72
    obic
    -0.71
     nuk
    -0.70
    POSITIVE LOGITS
     leave
    5.09
    leave
    3.77
     Leave
    3.72
    Leave
    3.66
     leaves
    3.47
     LEAVE
    2.95
    LEAVE
    2.84
     Leaves
    2.72
    leaves
    2.58
    Leaves
    2.56
    Act Density 0.054%

    No Known Activations