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

    Neuronpedia

    INDEX
    Explanations

    ari

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    vi
    -0.07
     Calder
    -0.07
     Ca
    -0.07
    _pro
    -0.06
    VERY
    -0.06
     بحث
    -0.06
     LANG
    -0.06
     facilitates
    -0.06
    psych
    -0.06
     bureaucratic
    -0.06
    POSITIVE LOGITS
    	payload
    0.07
    sexy
    0.06
    лон
    0.06
     eliminar
    0.06
    follower
    0.06
    (GameObject
    0.06
     accessible
    0.06
    .counter
    0.06
     bunny
    0.06
    .analysis
    0.06
    Act Density 0.000%

    No Known Activations