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

    Neuronpedia

    INDEX
    Explanations

    Scientific study results

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    inka
    -0.06
     unit
    -0.06
     shine
    -0.06
     dated
    -0.06
    GX
    -0.06
    ｲ
    -0.06
    važ
    -0.06
    _detection
    -0.06
     Feast
    -0.06
    isto
    -0.06
    POSITIVE LOGITS
     ESPN
    0.07
    urbation
    0.07
    .trade
    0.06
     Cambridge
    0.06
     dosp
    0.06
    ulares
    0.06
     Carl
    0.06
    	stat
    0.06
     المغ
    0.06
     etti
    0.06
    Act Density 0.039%

    No Known Activations