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

    Neuronpedia

    INDEX
    Explanations

    code, grammars

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     therapist
    -0.07
    COVER
    -0.07
     tokens
    -0.07
    BEL
    -0.07
    iability
    -0.06
    undra
    -0.06
    ético
    -0.06
     STORE
    -0.06
    рощ
    -0.06
     specification
    -0.06
    POSITIVE LOGITS
    階
    0.07
    /terms
    0.07
    (torch
    0.07
    akeFromNib
    0.06
     갤로그로
    0.06
     Colon
    0.06
    "path
    0.06
    ﾄ
    0.06
    _errno
    0.06
     Aster
    0.06
    Act Density 0.035%

    No Known Activations