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

    Neuronpedia

    INDEX
    Explanations

    Questions and answers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Pane
    -0.07
     Yale
    -0.06
     corridors
    -0.06
    -U
    -0.06
     Nightmare
    -0.06
    Editing
    -0.06
    ün
    -0.06
     insurers
    -0.06
     agreement
    -0.06
     Wer
    -0.06
    POSITIVE LOGITS
    [text
    0.06
    EAR
    0.06
     tipping
    0.06
    -effect
    0.06
    ，也
    0.06
    _normalized
    0.06
     розта
    0.06
    Downloads
    0.06
    ทำให
    0.06
    摄
    0.06
    Act Density 0.032%

    No Known Activations