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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     inauguration
    -0.07
     chopped
    -0.07
    .party
    -0.06
     detox
    -0.06
     trailed
    -0.06
     درست
    -0.06
    panse
    -0.06
    	damage
    -0.06
    .har
    -0.06
     dual
    -0.06
    POSITIVE LOGITS
    MessageBox
    0.07
    _PARAMETER
    0.07
     Lisa
    0.06
     betrayed
    0.06
     कभ
    0.06
    FLOW
    0.06
    ░
    0.06
    idor
    0.06
     française
    0.06
    тии
    0.06
    Act Density 0.000%

    No Known Activations