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

    Neuronpedia

    INDEX
    Explanations

    log data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SEXP
    -0.06
     Suzanne
    -0.06
    ruba
    -0.06
     Pazar
    -0.06
     cunning
    -0.06
    formatter
    -0.06
    Tracks
    -0.06
    .dir
    -0.06
    (timeout
    -0.06
    _DETECT
    -0.06
    POSITIVE LOGITS
     divers
    0.07
    ↵↵↵↵↵↵↵↵↵↵
    0.06
     отк
    0.06
     activeClassName
    0.06
     اص
    0.06
     Impl
    0.06
     indispens
    0.06
     singleton
    0.06
    liv
    0.06
     ac
    0.06
    Act Density 0.006%

    No Known Activations