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

    Neuronpedia

    INDEX
    Explanations

    offering to elaborate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    pare
    0.59
    ch
    0.56
    nip
    0.51
    นำ
    0.47
    t
    0.46
    Us
    0.45
    INC
    0.45
    IS
    0.45
    b
    0.45
    FAC
    0.44
    POSITIVE LOGITS
     creencias
    0.82
     interesses
    0.80
     saludos
    0.79
     tohoto
    0.79
     HUOBI
    0.79
     sonho
    0.78
     cuidadosamente
    0.77
     sonhos
    0.77
    Thats
    0.76
     teşekkür
    0.76
    Act Density 0.073%

    No Known Activations