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

    Neuronpedia

    INDEX
    Explanations

    each

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .CompareTo
    -0.07
    "Our
    -0.07
     doors
    -0.07
     gehört
    -0.07
    iversary
    -0.07
     overturn
    -0.07
     grateful
    -0.06
    _CLOSE
    -0.06
     انجام
    -0.06
     แ
    -0.06
    POSITIVE LOGITS
    etz
    0.06
    difference
    0.06
    วาม
    0.06
    !↵↵
    0.06
    /*------------------------------------------------
    0.06
    čet
    0.06
     تجاری
    0.06
    věl
    0.06
     each
    0.06
    weakSelf
    0.06
    Act Density 0.034%

    No Known Activations