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

    Neuronpedia

    INDEX
    Explanations

    these

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kodi
    -0.07
     Clintons
    -0.06
    pire
    -0.06
     meteor
    -0.06
     ماك
    -0.06
    Shapes
    -0.06
     Weg
    -0.06
     gc
    -0.06
    Probe
    -0.06
    probe
    -0.06
    POSITIVE LOGITS
    :bg
    0.07
     انسانی
    0.06
    keypress
    0.06
    _license
    0.06
     esto
    0.06
     W
    0.06
    เกษตร
    0.06
     넣
    0.06
    喜
    0.06
    _roll
    0.06
    Act Density 0.013%

    No Known Activations