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

    Neuronpedia

    INDEX
    Explanations

    .collect

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     quoted
    -0.07
    _SEP
    -0.07
    ož
    -0.07
    arshal
    -0.07
    _YEAR
    -0.07
    ovým
    -0.06
    hat
    -0.06
    ня
    -0.06
    -zero
    -0.06
    -level
    -0.06
    POSITIVE LOGITS
    dney
    0.06
    　イ
    0.06
     palp
    0.06
    .Dropout
    0.06
    σωπ
    0.06
     комплекс
    0.06
    AMS
    0.06
    Immediately
    0.06
    اح
    0.06
    `}↵
    0.06
    Act Density 0.004%

    No Known Activations