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

    Neuronpedia

    INDEX
    Explanations

    JSON data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IDENT
    -0.08
    rid
    -0.06
    .radians
    -0.06
    Quest
    -0.06
     Bull
    -0.06
    nia
    -0.06
    怨
    -0.06
    acher
    -0.06
    不定
    -0.06
     mountains
    -0.06
    POSITIVE LOGITS
    "]);↵
    0.07
     elgg
    0.07
    .Aggressive
    0.07
     krb
    0.07
    (Transaction
    0.07
     opposing
    0.07
     wzglę
    0.07
     Thankfully
    0.07
    ']));
    0.07
     +#+#+#+#+#+
    0.07
    Act Density 0.062%

    No Known Activations