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

    Neuronpedia

    INDEX
    Explanations

    former

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    anj
    -0.06
     땅
    -0.06
    |--------------------------------------------------------------------------↵
    -0.06
    @param
    -0.06
     Hemp
    -0.06
    _Post
    -0.06
     hjem
    -0.06
     السم
    -0.06
    ­t
    -0.06
    (itemId
    -0.06
    POSITIVE LOGITS
    怕
    0.07
     grouping
    0.06
    료
    0.06
    ديث
    0.06
    thought
    0.06
    JSON
    0.06
    ользов
    0.06
    rollo
    0.06
     Policies
    0.06
     Ор
    0.06
    Act Density 0.004%

    No Known Activations