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

    Neuronpedia

    INDEX
    Explanations

    estimates, approximations, calculations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ка
    0.64
    ဟုတ်
    0.53
     От
    0.48
     There
    0.48
    ون
    0.47
     To
    0.47
     Correlations
    0.47
     in
    0.47
     Provides
    0.47
     этом
    0.46
    POSITIVE LOGITS
    EL
    0.55
    '
    0.54
    3
    0.52
    ET
    0.51
     milhões
    0.50
    為
    0.48
     mãe
    0.47
     variável
    0.47
    EN
    0.46
     máxima
    0.46
    Act Density 0.410%

    No Known Activations