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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    kaz
    -0.06
     ayud
    -0.06
    _vote
    -0.06
    _ctr
    -0.06
    本当
    -0.06
     tří
    -0.06
     Decl
    -0.06
    Boxes
    -0.06
    ствует
    -0.06
    资产
    -0.06
    POSITIVE LOGITS
    T
    0.07
     Donald
    0.07
    ijk
    0.07
    .organ
    0.06
    bear
    0.06
    ArgumentException
    0.06
    _Array
    0.06
     approximate
    0.06
     опас
    0.06
     COOKIE
    0.06
    Act Density 0.000%

    No Known Activations