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

    Neuronpedia

    INDEX
    Explanations

    punctuation and symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    eid
    -0.07
    े
    -0.07
    ი
    -0.07
    ի
    -0.07
    ью
    -0.07
     Beat
    -0.07
    🎲
    -0.06
    /****************************************************************
    -0.06
    ileen
    -0.06
    리
    -0.06
    POSITIVE LOGITS
    onces
    0.07
    خص
    0.07
    ств
    0.07
     gamers
    0.06
    팎
    0.06
    منظ
    0.06
    getNum
    0.06
     permite
    0.06
     selon
    0.06
    ʝ
    0.06
    Act Density 0.062%

    No Known Activations