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

    Neuronpedia

    INDEX
    Explanations

    AM/PM time formatting

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _DEPEND
    -0.07
    _rc
    -0.06
     precio
    -0.06
     AppDelegate
    -0.06
    _area
    -0.06
     سپتامبر
    -0.06
     의미
    -0.06
     Nicolas
    -0.06
    CheckBox
    -0.06
    _metric
    -0.06
    POSITIVE LOGITS
    .Public
    0.07
    aar
    0.06
    APPER
    0.06
     surrogate
    0.06
    \Auth
    0.06
     αρ
    0.06
    어서
    0.06
    عان
    0.06
     eğit
    0.06
    382
    0.06
    Act Density 0.011%

    No Known Activations