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

    Neuronpedia

    INDEX
    Explanations

    code/data snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    🚪
    -0.07
    _AND
    -0.07
    _JUMP
    -0.07
    ဏ
    -0.06
    떵
    -0.06
    Ѐ
    -0.06
    ’s
    -0.06
    噘
    -0.06
     LEFT
    -0.06
     Timeout
    -0.06
    POSITIVE LOGITS
     Fund
    0.08
    鸥
    0.07
    发行
    0.07
    עין
    0.07
     continents
    0.07
     faithful
    0.07
    鹿
    0.07
     misma
    0.07
     hospital
    0.06
     Luna
    0.06
    Act Density 0.025%

    No Known Activations