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

    Neuronpedia

    INDEX
    Explanations

    penalty and fees

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     accountability
    0.47
     Dz
    0.45
     Accountability
    0.45
     işlem
    0.44
     Pendidikan
    0.43
     interventi
    0.43
     cotisation
    0.42
    ారీ
    0.42
     legisl
    0.42
    支払
    0.41
    POSITIVE LOGITS
     penalty
    1.18
    Penalty
    1.05
    penalty
    1.02
     penalties
    1.01
     Penalty
    0.96
     penalized
    0.93
     Penal
    0.93
     penal
    0.86
     штра
    0.66
    罰
    0.64
    Act Density 0.017%

    No Known Activations