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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     přičemž
    -0.07
    -sex
    -0.06
     Imm
    -0.06
     doom
    -0.06
    ární
    -0.06
    .CheckBox
    -0.06
     grinder
    -0.06
     dopad
    -0.06
    FOX
    -0.06
     Cla
    -0.06
    POSITIVE LOGITS
     واست
    0.07
     sanctions
    0.07
    igated
    0.06
    BALL
    0.06
    lated
    0.06
     باغ
    0.06
     красив
    0.06
    ществ
    0.06
    ->__
    0.06
    ,default
    0.06
    Act Density 0.015%

    No Known Activations