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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    阿里巴巴
    -0.07
    adas
    -0.07
     Alien
    -0.07
     Ethiopia
    -0.07
     boasting
    -0.07
    铖
    -0.07
    	final
    -0.07
    ebile
    -0.06
    进攻
    -0.06
    פחד
    -0.06
    POSITIVE LOGITS
     licens
    0.07
    /oct
    0.07
     Vocal
    0.07
    收
    0.07
    _ratings
    0.07
     hearings
    0.07
    pager
    0.07
     DAL
    0.07
     MUCH
    0.07
    诧
    0.07
    Act Density 0.071%

    No Known Activations