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

    Neuronpedia

    INDEX
    Explanations

    numerical data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Component
    -0.07
    辐
    -0.07
    髋
    -0.07
     fanc
    -0.07
    珲
    -0.07
     EVE
    -0.06
     evasion
    -0.06
     expressive
    -0.06
     postponed
    -0.06
     flush
    -0.06
    POSITIVE LOGITS
    _targets
    0.07
    ToLocal
    0.07
     BJ
    0.07
     soaking
    0.07
    .pr
    0.07
     проц
    0.07
     cityName
    0.07
    /dialog
    0.07
     heroes
    0.07
    (alias
    0.07
    Act Density 0.061%

    No Known Activations