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

    Neuronpedia

    INDEX
    Explanations

    ler

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    star
    -0.06
    urt
    -0.06
    लग
    -0.06
     Positive
    -0.06
    _write
    -0.06
     Race
    -0.06
    -setting
    -0.06
     transmitted
    -0.06
    ausal
    -0.06
     Effect
    -0.06
    POSITIVE LOGITS
     IDM
    0.07
     nbr
    0.06
    皮
    0.06
     manten
    0.06
     nhé
    0.06
     لینک
    0.06
     jap
    0.06
     LG
    0.06
     Jap
    0.06
     InvalidOperationException
    0.06
    Act Density 0.000%

    No Known Activations