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

    Neuronpedia

    INDEX
    Explanations

    code/syntax

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.08
    蚝
    -0.06
     echt
    -0.06
    -prepend
    -0.06
    ."',
    -0.06
    ᅳ
    -0.06
     yeni
    -0.06
     glass
    -0.06
    上游
    -0.06
    Ŷ
    -0.06
    POSITIVE LOGITS
    /memory
    0.08
    _IDENT
    0.07
    Wood
    0.07
    _IA
    0.07
    いか
    0.07
     thế
    0.07
     kullan
    0.07
     quốc
    0.06
     incorrectly
    0.06
    .Form
    0.06
    Act Density 0.001%

    No Known Activations