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

    Neuronpedia

    INDEX
    Explanations

    attacks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    니아
    -0.07
     جام
    -0.07
    ф
    -0.07
    _PROGRESS
    -0.06
     trest
    -0.06
    gı
    -0.06
    .ToolStripItem
    -0.06
     Insurance
    -0.06
     HEIGHT
    -0.06
    [#
    -0.06
    POSITIVE LOGITS
    щин
    0.06
     Ut
    0.06
    غل
    0.06
    Heading
    0.06
     hear
    0.06
    idence
    0.06
     cdecl
    0.06
    ớm
    0.05
    configs
    0.05
     hateful
    0.05
    Act Density 0.023%

    No Known Activations