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

    Neuronpedia

    INDEX
    Explanations

    treatment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    send
    -0.07
    Ќ
    -0.07
     وكذلك
    -0.07
     conject
    -0.07
    sz
    -0.07
     ₹
    -0.07
     SOFTWARE
    -0.07
     anderen
    -0.07
    属于
    -0.07
    .Request
    -0.07
    POSITIVE LOGITS
    gba
    0.07
     booster
    0.07
    Gradient
    0.07
    *d
    0.07
    guards
    0.07
    orners
    0.07
    批发
    0.06
    instant
    0.06
    международн
    0.06
    _ORIGIN
    0.06
    Act Density 0.079%

    No Known Activations