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

    Neuronpedia

    INDEX
    Explanations

    Mathematical equations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _STORE
    -0.07
    新人玩家
    -0.07
    ユー�
    -0.07
     européenne
    -0.07
    wingConstants
    -0.07
    全局
    -0.07
    ServletContext
    -0.07
    '")↵
    -0.06
    quam
    -0.06
    Foreground
    -0.06
    POSITIVE LOGITS
    Meet
    0.08
    一件事
    0.07
    abella
    0.07
    #/
    0.07
    oteca
    0.07
     swallowing
    0.07
    =/
    0.07
     scarcity
    0.07
    癌
    0.06
    &w
    0.06
    Act Density 0.023%

    No Known Activations