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

    Neuronpedia

    INDEX
    Explanations

    Code Snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    🐼
    -0.08
    [NUM
    -0.07
    _TEM
    -0.07
     Heg
    -0.07
     SUCCESS
    -0.07
     UIButton
    -0.07
    箦
    -0.07
    iphone
    -0.07
     Hindus
    -0.07
    𝗝
    -0.07
    POSITIVE LOGITS
     reaches
    0.08
    爟
    0.07
    Clickable
    0.07
     sketches
    0.07
     system
    0.07
     consider
    0.06
    險
    0.06
     экон
    0.06
    .iso
    0.06
    /o
    0.06
    Act Density 0.042%

    No Known Activations