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

    Neuronpedia

    INDEX
    Explanations

    )(

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dıkt
    -0.08
     tịch
    -0.07
     conte
    -0.07
    ,’”
    -0.07
    新版
    -0.06
    尿
    -0.06
     immune
    -0.06
     הודעה
    -0.06
     Adventure
    -0.06
     leve
    -0.06
    POSITIVE LOGITS
     Darkness
    0.07
     be
    0.07
    电台
    0.07
    洗
    0.07
     wash
    0.07
    orghini
    0.07
    arness
    0.06
    流入
    0.06
    的压力
    0.06
    (ra
    0.06
    Act Density 0.001%

    No Known Activations