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

    Neuronpedia

    INDEX
    Explanations

    hours

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Barber
    -0.08
    eson
    -0.07
     Above
    -0.07
    𝑆
    -0.07
    COVER
    -0.07
     Chili
    -0.07
    Station
    -0.06
    这场
    -0.06
    War
    -0.06
     demolished
    -0.06
    POSITIVE LOGITS
    胯
    0.08
    _conv
    0.07
    intersect
    0.07
    traits
    0.07
    נצי
    0.07
     Interpreter
    0.07
    僦
    0.07
    .throw
    0.07
    ubectl
    0.06
    鳉
    0.06
    Act Density 0.102%

    No Known Activations