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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    '=>$_
    -0.08
     structured
    -0.07
    中介
    -0.07
    具
    -0.07
    ◔
    -0.07
    Frames
    -0.07
    反映
    -0.07
     Equipment
    -0.06
    ,null
    -0.06
    的心情
    -0.06
    POSITIVE LOGITS
     adidas
    0.08
    垙
    0.08
     pornos
    0.07
    amos
    0.07
     alguns
    0.07
     nodded
    0.07
     RAID
    0.07
    𝒐
    0.07
    בעיות
    0.07
     conectar
    0.06
    Act Density 0.069%

    No Known Activations