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

    Neuronpedia

    INDEX
    Explanations

    actions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     frank
    -0.07
    )const
    -0.07
    ("?
    -0.07
     ValidationError
    -0.06
    _mat
    -0.06
    าศาสตร
    -0.06
    098
    -0.06
    .getFloat
    -0.06
     través
    -0.06
    ařilo
    -0.06
    POSITIVE LOGITS
    돌
    0.07
    peech
    0.07
    _sign
    0.07
    EEP
    0.07
     actions
    0.06
    	
↵	
↵
    0.06
    .nih
    0.06
     위
    0.06
    付
    0.06
    run
    0.06
    Act Density 0.050%

    No Known Activations