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

    Neuronpedia

    INDEX
    Explanations

    active

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bathroom
    -0.08
     LJ
    -0.07
     saturation
    -0.07
     TK
    -0.07
    /change
    -0.07
     genetic
    -0.07
     Contrast
    -0.07
     khoảng
    -0.07
    Treatment
    -0.07
    参观
    -0.06
    POSITIVE LOGITS
    Ӆ
    0.07
     directories
    0.07
    パタ
    0.07
     economists
    0.07
    面上
    0.07
     //!
    0.07
     "";
    0.06
    UUID
    0.06
     quotas
    0.06
    �
    0.06
    Act Density 0.002%

    No Known Activations