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

    Neuronpedia

    INDEX
    Explanations

    study dates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cale
    -0.07
    Invocation
    -0.06
    맻
    -0.06
    诘
    -0.06
     dare
    -0.06
    썰
    -0.06
     sense
    -0.06
    ae
    -0.06
    呼吸
    -0.06
    /graph
    -0.06
    POSITIVE LOGITS
     absl
    0.07
     شبكة
    0.07
    丢了
    0.07
    NET
    0.07
    tickets
    0.07
     Außerdem
    0.07
    تسليم
    0.07
    idders
    0.07
     IService
    0.07
     Streaming
    0.07
    Act Density 0.010%

    No Known Activations