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

    Neuronpedia

    INDEX
    Explanations

    engaging everyone, appealing to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Chiara
    0.93
     Marbella
    0.93
     Shibuya
    0.91
    Provence
    0.91
     Puebla
    0.91
    Skew
    0.91
     Salamanca
    0.91
    뀨
    0.89
    Kuota
    0.89
     conflictos
    0.88
    POSITIVE LOGITS
     rapidly
    0.67
    в
    0.65
    uer
    0.63
    гене
    0.62
    ining
    0.62
    ée
    0.61
    imer
    0.61
    omer
    0.60
     vigorously
    0.60
    mp
    0.60
    Act Density 0.001%

    No Known Activations