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

    Neuronpedia

    INDEX
    Explanations

    classical

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ideos
    -0.08
    MMdd
    -0.07
    (values
    -0.07
    RF
    -0.07
     correlated
    -0.07
    ↵     ↵
    -0.07
    抗日
    -0.07
    .recv
    -0.07
     typeName
    -0.07
    brook
    -0.06
    POSITIVE LOGITS
    确实
    0.07
     Sol
    0.07
     соб
    0.07
    .eng
    0.07
    -progress
    0.07
    -function
    0.07
    _ptr
    0.07
    glass
    0.07
     trapped
    0.07
     trap
    0.07
    Act Density 0.021%

    No Known Activations