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

    Neuronpedia

    INDEX
    Explanations

    primal instincts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ız
    -0.07
    ᴳ
    -0.07
    	Object
    -0.07
    -alpha
    -0.07
    🚜
    -0.07
    —that
    -0.07
    .thread
    -0.07
     swell
    -0.07
    놋
    -0.07
     National
    -0.07
    POSITIVE LOGITS
    FT
    0.07
    _NAMES
    0.07
     jogador
    0.07
    .toolbox
    0.07
    こんに
    0.07
     Sinn
    0.06
    OUNDS
    0.06
    ************************************************
    0.06
    Matches
    0.06
    مم
    0.06
    Act Density 0.045%

    No Known Activations