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

    Neuronpedia

    INDEX
    Explanations

    plane

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     aggreg
    -0.07
    3
    -0.07
    scious
    -0.07
    ++){↵
    -0.07
    .tax
    -0.07
    -0.06
    ʊ
    -0.06
    ღ
    -0.06
    承德
    -0.06
    alous
    -0.06
    POSITIVE LOGITS
    궕
    0.07
    仞
    0.07
    апр
    0.07
    佥
    0.07
    뱔
    0.07
    enis
    0.07
    平面
    0.07
    TransparentColor
    0.07
    换句话
    0.07
    ∨
    0.07
    Act Density 0.010%

    No Known Activations