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

    Neuronpedia

    INDEX
    Explanations

    SELECT

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     madrid
    -0.08
    ホテル
    -0.08
    تحد
    -0.07
    乙烯
    -0.07
     Perth
    -0.07
     thuê
    -0.07
     ContentType
    -0.07
     proyectos
    -0.07
     ipv
    -0.07
    千万别
    -0.07
    POSITIVE LOGITS
    oscopic
    0.08
    .Focused
    0.07
    PLOY
    0.07
     occupation
    0.07
    倚
    0.07
    DEST
    0.07
    acus
    0.07
    排骨
    0.07
    指着
    0.07
    压制
    0.07
    Act Density 0.009%

    No Known Activations