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

    Neuronpedia

    INDEX
    Explanations

    rect

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ()==
    -0.08
    -su
    -0.08
     Achievement
    -0.07
    _nonce
    -0.07
    ched
    -0.07
    正能量
    -0.07
     CHE
    -0.07
    不算
    -0.07
    nde
    -0.07
     ingredient
    -0.07
    POSITIVE LOGITS
     jov
    0.07
     club
    0.06
     الإلك
    0.06
     Rugby
    0.06
    ∶
    0.06
     الاستث
    0.06
    vey
    0.06
    ¯¯¯¯
    0.06
    ��
    0.06
    箭
    0.06
    Act Density 0.001%

    No Known Activations