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

    Neuronpedia

    INDEX
    Explanations

    brief

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	cnt
    -0.07
     Areas
    -0.07
    _s
    -0.06
     Chavez
    -0.06
    Ѕ
    -0.06
     novels
    -0.06
    finder
    -0.06
    original
    -0.06
    [next
    -0.06
     Regents
    -0.06
    POSITIVE LOGITS
    월
    0.07
    ░
    0.07
    جام
    0.06
    _SIGN
    0.06
    oolStrip
    0.06
    去
    0.06
     بج
    0.06
     элек
    0.06
    QU
    0.06
     Greenwich
    0.06
    Act Density 0.013%

    No Known Activations