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

    Neuronpedia

    INDEX
    Explanations

    Avoidance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ç©´
    -0.28
    run
    -0.27
    UFFIX
    -0.26
    olerance
    -0.25
    sleep
    -0.25
    ç¼ĸåī§
    -0.25
     separation
    -0.25
     run
    -0.24
    à¸ĩ
    -0.24
    ä¸įèĤ¯
    -0.24
    POSITIVE LOGITS
    anean
    0.28
     vision
    0.27
    DataRow
    0.27
    á»ģm
    0.27
     ÅĽrod
    0.26
    awesome
    0.25
    >Last
    0.25
    agram
    0.25
    hammad
    0.25
    ieval
    0.24
    Act Density 0.172%

    No Known Activations