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

    Neuronpedia

    INDEX
    Explanations

    and or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tershire
    -0.42
    ſelf
    -0.41
     relationships
    -0.41
     illa
    -0.41
    alapa
    -0.40
    hanna
    -0.39
     dita
    -0.39
    wiſe
    -0.38
    iální
    -0.38
     relations
    -0.38
    POSITIVE LOGITS
    ########.
    0.86
     kasarigan
    0.81
    KommentareTeilen
    0.79
    脚注の使い方
    0.76
    BeginInit
    0.75
     cherchés
    0.71
    出版年
    0.70
    providedIn
    0.69
    KURZBESCHREIBUNG
    0.69
    bootstrapcdn
    0.69
    Act Density 0.010%

    No Known Activations