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

    Neuronpedia

    INDEX
    Explanations

    Heroism

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     doom
    -0.07
    Φ
    -0.07
     writes
    -0.06
     Silence
    -0.06
    SY
    -0.06
     �
    -0.06
    _page
    -0.06
     Trace
    -0.06
     Phot
    -0.06
    Ind
    -0.06
    POSITIVE LOGITS
    -wh
    0.07
    ollectors
    0.07
    _support
    0.06
    _location
    0.06
    TPL
    0.06
     mutated
    0.06
     colored
    0.06
     Babies
    0.06
     ủy
    0.06
    ))]↵
    0.06
    Act Density 0.144%

    No Known Activations