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

    Neuronpedia

    INDEX
    Explanations

    ries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     är
    -0.07
     Infos
    -0.07
     WG
    -0.07
    _connector
    -0.07
    uliar
    -0.07
     dahil
    -0.06
     새글
    -0.06
    ทาน
    -0.06
    usive
    -0.06
     multer
    -0.06
    POSITIVE LOGITS
     prevState
    0.07
     auditor
    0.06
     vaguely
    0.06
     punctuation
    0.06
    Charset
    0.06
    amaha
    0.06
     stumble
    0.06
    _console
    0.06
     Psychological
    0.06
    tenant
    0.06
    Act Density 0.000%

    No Known Activations