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

    Neuronpedia

    INDEX
    Explanations

    I am / I understand / I cannot

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :
    0.85
    ;
    0.82
     by
    0.80
    },
    0.79
    ,
    0.79
    .
    0.77
     -
    0.75
     the
    0.74
    ,"
    0.70
     during
    0.69
    POSITIVE LOGITS
     نے
    0.68
    aculate
    0.68
    Phones
    0.66
    ਨ੍ਹਾਂ
    0.65
    げ
    0.65
    쁜
    0.65
    垐
    0.65
    㤈
    0.64
    utenant
    0.63
    brahim
    0.63
    Act Density 0.060%

    No Known Activations