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

    Neuronpedia

    INDEX
    Explanations

    explaining possibilities in Spanish

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lice
    0.63
    dere
    0.53
    lle
    0.52
    bolts
    0.51
    دو
    0.50
    Attractive
    0.50
    lip
    0.50
    ंना
    0.49
    jian
    0.49
    Inte
    0.49
    POSITIVE LOGITS
     martyrdom
    0.46
     averaged
    0.46
     whipped
    0.45
     weakness
    0.45
     zawod
    0.44
     squadra
    0.44
     although
    0.44
    0.43
     nausea
    0.43
     tossed
    0.43
    Act Density 0.003%

    No Known Activations