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

    Neuronpedia

    INDEX
    Explanations

    focus

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dedicated
    -0.07
     divisions
    -0.07
     těl
    -0.07
    .parts
    -0.06
     Bodies
    -0.06
     toda
    -0.06
    بين
    -0.06
     ενός
    -0.06
    �
    -0.06
    laden
    -0.06
    POSITIVE LOGITS
    prot
    0.07
     WTF
    0.06
     Peygamber
    0.06
    ообраз
    0.06
     النه
    0.06
    _fd
    0.06
    aguay
    0.06
    ๑
    0.06
     Swagger
    0.06
    ุด
    0.06
    Act Density 0.009%

    No Known Activations