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

    Neuronpedia

    INDEX
    Explanations

    mean

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    icted
    -0.07
    aných
    -0.07
    OfSize
    -0.06
     replied
    -0.06
    phase
    -0.06
    MSG
    -0.06
     평당
    -0.06
     �
    -0.06
    (before
    -0.06
     Boss
    -0.06
    POSITIVE LOGITS
    $menu
    0.06
    Indices
    0.06
    ientras
    0.06
    减
    0.06
    ataires
    0.06
    ?“
    0.06
    Physical
    0.06
    VEC
    0.06
    orum
    0.06
    
    0.06
    Act Density 0.008%

    No Known Activations