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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /Delete
    -0.07
    _shortcode
    -0.06
    .sources
    -0.06
    yslu
    -0.06
    “When
    -0.06
    assets
    -0.06
     psychotic
    -0.06
    째
    -0.06
     camb
    -0.06
     або
    -0.06
    POSITIVE LOGITS
    %
    0.07
    'l
    0.07
    gi
    0.07
    endency
    0.06
     Sci
    0.06
    +h
    0.06
     cats
    0.06
    Candidate
    0.06
    Team
    0.06
     But
    0.06
    Act Density 0.013%

    No Known Activations