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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    don
    -0.07
    info
    -0.07
    Dani
    -0.07
    kowski
    -0.07
    76
    -0.06
    oba
    -0.06
     Freder
    -0.06
    _pdf
    -0.06
    enemy
    -0.06
     memories
    -0.06
    POSITIVE LOGITS
    [hash
    0.07
     GS
    0.06
    ERE
    0.06
    [Z
    0.06
     متفاوت
    0.06
    951
    0.06
    [List
    0.06
    知道
    0.06
    ^K
    0.06
    _RCC
    0.06
    Act Density 0.005%

    No Known Activations