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

    Neuronpedia

    INDEX
    Explanations

    programming/code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     směrem
    -0.07
    pově
    -0.07
    _charset
    -0.07
    icycle
    -0.07
    (element
    -0.07
    _dump
    -0.07
     conservative
    -0.06
    ″N
    -0.06
    建立
    -0.06
     convergence
    -0.06
    POSITIVE LOGITS
     merch
    0.06
    빈
    0.06
     Batman
    0.06
     sendData
    0.06
    );
↵
↵
↵
    0.05
    ês
    0.05
    offset
    0.05
     yr
    0.05
    suppress
    0.05
    "))↵
    0.05
    Act Density 0.141%

    No Known Activations