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

    Neuronpedia

    INDEX
    Explanations

    medical authorizations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .getPath
    -0.07
    롤
    -0.07
     одному
    -0.07
     kite
    -0.06
     어떻게
    -0.06
     bite
    -0.06
     spat
    -0.06
    资
    -0.06
    :'+
    -0.06
     Those
    -0.06
    POSITIVE LOGITS
    =S
    0.06
    ‐‐
    0.06
    (...)↵
    0.06
    uation
    0.06
    JV
    0.06
    gers
    0.06
    preserve
    0.06
    _IDENTIFIER
    0.05
    _sentence
    0.05
    (goal
    0.05
    Act Density 0.044%

    No Known Activations