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

    Neuronpedia

    INDEX
    Explanations

    admissions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    다면
    -0.06
     mig
    -0.06
     ------------------------------------------------------------------------------------------------
    -0.06
     알고
    -0.06
     Santiago
    -0.06
    _l
    -0.06
    expects
    -0.06
    <i
    -0.06
     AAA
    -0.05
     अम
    -0.05
    POSITIVE LOGITS
     を
    0.07
     caus
    0.07
    ęki
    0.07
    ouv
    0.07
    >//
    0.07
    .quote
    0.06
    ocrisy
    0.06
    Sau
    0.06
    TRAIN
    0.06
     Surrey
    0.06
    Act Density 0.017%

    No Known Activations