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

    Neuronpedia

    INDEX
    Explanations

    sequences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _factors
    -0.09
    🎫
    -0.08
    }],↵
    -0.07
    "))↵
    -0.07
     controversy
    -0.07
    伍
    -0.07
     CLOSED
    -0.07
    更深
    -0.07
    ()))
↵
    -0.07
    traditional
    -0.07
    POSITIVE LOGITS
     RMS
    0.07
    (alert
    0.07
    Sharp
    0.07
    (alias
    0.07
    럴
    0.07
    lemetry
    0.07
    ());//
    0.07
    Mounted
    0.07
     מיד
    0.07
    酸
    0.07
    Act Density 0.016%

    No Known Activations