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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    躔
    -0.07
    ⋆
    -0.07
    /workspace
    -0.07
    ?key
    -0.07
    ⚠
    -0.07
    SingleNode
    -0.07
    Ḱ
    -0.06
    大众
    -0.06
     Shirley
    -0.06
    详细
    -0.06
    POSITIVE LOGITS
     Lexer
    0.07
     Timber
    0.07
     lavor
    0.07
     sac
    0.07
     Aw
    0.07
     schle
    0.07
    (boolean
    0.07
    _wc
    0.07
     lm
    0.06
     fighters
    0.06
    Act Density 0.008%

    No Known Activations