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

    Neuronpedia

    INDEX
    Explanations

    determining whether

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     climbing
    0.50
     Climbing
    0.48
    ,
    0.42
    land
    0.41
    Ler
    0.41
    Pherson
    0.41
     এখন
    0.40
    澄清
    0.40
    Argonne
    0.40
    alet
    0.40
    POSITIVE LOGITS
    голо
    0.54
    ступа
    0.51
    сибо
    0.50
    хбет
    0.49
     банка
    0.48
    тта
    0.48
     huesos
    0.48
     pamoja
    0.48
    ون
    0.48
    සු
    0.48
    Act Density 0.000%

    No Known Activations