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

    Neuronpedia

    INDEX
    Explanations

    Math expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rivière
    -0.08
     retreat
    -0.08
     عب
    -0.08
    _supported
    -0.08
    EPT
    -0.08
    ベント
    -0.08
    最快
    -0.08
    גם
    -0.08
    ([[
    -0.08
     परीक्षण
    -0.08
    POSITIVE LOGITS
     moments
    0.08
     Cemetery
    0.08
    rings
    0.07
    Mom
    0.07
     தே
    0.07
     momentos
    0.07
    ingss
    0.07
     происходит
    0.07
     préparation
    0.07
     realities
    0.07
    Act Density 0.127%

    No Known Activations