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

    Neuronpedia

    INDEX
    Explanations

    relationships and attraction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ]);
    -0.07
    (ST
    -0.07
    POS
    -0.07
     Eve
    -0.07
     precursor
    -0.07
    _li
    -0.07
    Number
    -0.06
    ительного
    -0.06
     cuffs
    -0.06
    _OBJC
    -0.06
    POSITIVE LOGITS
     địch
    0.06
    atever
    0.06
     nghĩa
    0.06
    alers
    0.06
     Haut
    0.06
    加
    0.06
    �
    0.05
    čník
    0.05
    产生
    0.05
     не
    0.05
    Act Density 0.313%

    No Known Activations