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

    Neuronpedia

    INDEX
    Explanations

    community resources

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    []){↵
    -0.07
     nouveaux
    -0.07
    _fd
    -0.07
     deadlock
    -0.06
     ET
    -0.06
    Send
    -0.06
     Giving
    -0.06
    -INF
    -0.06
     land
    -0.06
     وهناك
    -0.06
    POSITIVE LOGITS
    ulsive
    0.08
     plano
    0.07
    .windows
    0.06
     "%
    0.06
    素质
    0.06
     analyzer
    0.06
    focused
    0.06
    .when
    0.06
    /cc
    0.06
     المق
    0.06
    Act Density 0.140%

    No Known Activations