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

    Neuronpedia

    INDEX
    Explanations

    spent time doing activities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sais
    1.27
     fécond
    1.13
     beho
    1.03
     amenazas
    1.02
     won
    1.01
    XVII
    0.96
    形势
    0.94
    £
    0.94
    ဍ
    0.93
     इरा
    0.93
    POSITIVE LOGITS
     pastime
    1.51
    ującego
    1.37
    𝘢
    1.34
     relaxing
    1.33
    外出
    1.33
    to
    1.26
    ającego
    1.24
    parks
    1.23
    をする
    1.21
    pada
    1.21
    Act Density 0.646%

    No Known Activations