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

    Neuronpedia

    INDEX
    Explanations

    olver

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (fh
    -0.06
     expenditures
    -0.06
     BPM
    -0.06
    Europe
    -0.06
    ([]);↵↵
    -0.06
    .ObjectMapper
    -0.06
     �
    -0.06
     conversion
    -0.06
    "}}>↵
    -0.06
    /settingsdialog
    -0.06
    POSITIVE LOGITS
    лятор
    0.08
     페
    0.07
     ‘
    0.07
     “
    0.07
    ισ
    0.07
    OSE
    0.07
     kháng
    0.06
     το
    0.06
     "
    0.06
    boxed
    0.06
    Act Density 0.009%

    No Known Activations