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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    FUN
    -0.06
     fragmentation
    -0.06
    dro
    -0.06
     ｲ
    -0.06
    الی
    -0.06
    -trans
    -0.06
    inceton
    -0.06
    openh
    -0.06
     말
    -0.06
     gode
    -0.06
    POSITIVE LOGITS
     Origins
    0.07
     ordeal
    0.07
     bedside
    0.07
    	GPIO
    0.07
    _ajax
    0.06
    นส
    0.06
     horr
    0.06
    _pal
    0.06
     volt
    0.06
    :CGPoint
    0.06
    Act Density 0.001%

    No Known Activations