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

    Neuronpedia

    INDEX
    Explanations

    intensity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     no
    -0.07
    "For
    -0.07
     RSS
    -0.06
     Proud
    -0.06
     literature
    -0.06
     hates
    -0.06
    .be
    -0.06
    “When
    -0.06
     For
    -0.06
    When
    -0.06
    POSITIVE LOGITS
    FunctionFlags
    0.07
    connexion
    0.07
     trauma
    0.07
    TEMPL
    0.06
    Stra
    0.06
    .WebServlet
    0.06
    DIST
    0.06
    VALUE
    0.06
    jed
    0.06
     enfants
    0.06
    Act Density 0.115%

    No Known Activations