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

    Neuronpedia

    INDEX
    Explanations

    life

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Maintain
    -0.07
     Suicide
    -0.07
    _count
    -0.07
    acency
    -0.07
    -cultural
    -0.07
     negatively
    -0.07
     "_"
    -0.06
     constrained
    -0.06
    .analysis
    -0.06
     internal
    -0.06
    POSITIVE LOGITS
     Actors
    0.06
     sel
    0.06
     italiane
    0.06
    ’util
    0.06
     cpp
    0.06
     tweeting
    0.06
    ERVED
    0.06
    uenta
    0.06
    稳
    0.06
    inya
    0.05
    Act Density 0.023%

    No Known Activations