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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     setuptools
    -0.08
     quantum
    -0.08
     �
    -0.08
     төл
    -0.08
     无限
    -0.08
     adgang
    -0.08
     unreasonable
    -0.08
    작성
    -0.08
     discapacidad
    -0.08
     Contributor
    -0.07
    POSITIVE LOGITS
    [],↵
    0.08
    paramref
    0.08
    .“↵↵
    0.08
    _corner
    0.08
     rooft
    0.07
     cling
    0.07
    corn
    0.07
    [];↵
    0.07
     corners
    0.07
    —↵
    0.07
    Act Density 0.018%

    No Known Activations