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

    Neuronpedia

    INDEX
    Explanations

    printed editions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     irq
    -0.07
    }}"↵
    -0.07
    参照
    -0.07
    頻
    -0.07
    irement
    -0.07
    vertime
    -0.07
     timeout
    -0.06
     Clover
    -0.06
     experimented
    -0.06
     december
    -0.06
    POSITIVE LOGITS
     económ
    0.07
    (ball
    0.07
     מש
    0.07
     positional
    0.07
    .returnValue
    0.07
    坚定不
    0.07
     Pow
    0.07
    _soft
    0.06
    .addColumn
    0.06
     Пос
    0.06
    Act Density 0.026%

    No Known Activations