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

    Neuronpedia

    INDEX
    Explanations

    time dimension comparisons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    悛
    0.43
    بال
    0.41
    ья
    0.41
    Ђ
    0.40
    悴
    0.40
    Ѓ
    0.40
     frontière
    0.40
    悪
    0.40
     dimensiones
    0.40
     prefque
    0.40
    POSITIVE LOGITS
     involving
    0.42
    lings
    0.41
    ıc
    0.41
    terne
    0.40
     increasingly
    0.39
     ribbons
    0.38
    lim
    0.38
     hitting
    0.38
    unica
    0.38
    asta
    0.38
    Act Density 0.000%

    No Known Activations