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

    Neuronpedia

    INDEX
    Explanations

    Code file information

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ographical
    -0.07
    Namespace
    -0.07
     microscope
    -0.07
    ERICA
    -0.06
    .Other
    -0.06
    ド
    -0.06
     micro
    -0.06
    .inline
    -0.06
    쏜
    -0.06
    ,Th
    -0.06
    POSITIVE LOGITS
    center
    0.07
     got
    0.07
    ஐ
    0.07
     just
    0.07
     dipped
    0.07
    当
    0.07
     cant
    0.07
    桂
    0.07
    还可以
    0.07
    _revision
    0.06
    Act Density 0.000%

    No Known Activations