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

    Neuronpedia

    INDEX
    Explanations

    Keyboard key press events

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    hom
    -0.09
    ftime
    -0.09
     Hom
    -0.08
    ously
    -0.08
    いう
    -0.08
     hom
    -0.07
    lees
    -0.07
    ptime
    -0.07
    い
    -0.07
    jours
    -0.07
    POSITIVE LOGITS
     restricting
    0.11
     restrict
    0.10
    Restr
    0.10
    禁止
    0.09
     Restr
    0.09
     restrictions
    0.09
     ingres
    0.09
     запрещ
    0.09
    Prevent
    0.09
    Restriction
    0.08
    Act Density 0.001%

    No Known Activations