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

    Neuronpedia

    INDEX
    Explanations

    ocket

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ,result
    -0.07
    tell
    -0.07
    我只是
    -0.07
    -motion
    -0.07
    ㍉
    -0.07
    "path
    -0.07
     estado
    -0.06
    antu
    -0.06
     المجلس
    -0.06
    sono
    -0.06
    POSITIVE LOGITS
    Encoded
    0.08
    }->{
    0.07
    sha
    0.07
     ASIC
    0.07
     parsing
    0.07
     Charm
    0.07
    Endpoint
    0.07
     checkpoint
    0.07
    キャ
    0.07
    agan
    0.07
    Act Density 0.000%

    No Known Activations