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

    Neuronpedia

    INDEX
    Explanations

    represent

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Optimizer
    -0.07
    acf
    -0.07
    ()/
    -0.07
     autom
    -0.07
    /blog
    -0.07
     deducted
    -0.07
    "=>"
    -0.07
     güzel
    -0.07
     corrective
    -0.07
     inhib
    -0.07
    POSITIVE LOGITS
    श
    0.08
    зыва
    0.08
    atham
    0.07
     Needs
    0.07
    CRY
    0.07
    brig
    0.07
    حيا
    0.07
    _TEX
    0.07
    煎
    0.07
    锵
    0.07
    Act Density 0.036%

    No Known Activations