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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pickle
    -0.07
     Duel
    -0.07
    ่าย
    -0.07
     Gujar
    -0.06
    충
    -0.06
    -al
    -0.06
     Chapman
    -0.06
    .lab
    -0.06
    	redirect
    -0.06
     bindings
    -0.06
    POSITIVE LOGITS
    anean
    0.07
    返
    0.06
    pción
    0.06
     №
    0.06
     mein
    0.06
    lesi
    0.06
     İslam
    0.06
    _FILES
    0.06
    east
    0.06
     authentic
    0.06
    Act Density 0.072%

    No Known Activations