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

    Neuronpedia

    INDEX
    Explanations

    strong negative judgment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     электро
    0.67
     possa
    0.66
    kében
    0.66
    irtual
    0.65
    杈
    0.64
     pudiera
    0.63
    Gioco
    0.63
     possam
    0.63
     pavatt
    0.62
    ambah
    0.62
    POSITIVE LOGITS
     awful
    1.93
     disgusting
    1.92
     horrible
    1.86
     appalling
    1.85
     horrifying
    1.77
     horrendous
    1.77
     hideous
    1.77
     horrific
    1.70
     atrocious
    1.69
     terrible
    1.68
    Act Density 0.398%

    No Known Activations