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

    Neuronpedia

    INDEX
    Explanations

    small

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Profit
    -0.06
     unwrap
    -0.06
    わたし
    -0.06
    _called
    -0.06
     relativ
    -0.06
    	callback
    -0.06
    Politics
    -0.06
    .dispatch
    -0.06
     rowspan
    -0.06
    redis
    -0.06
    POSITIVE LOGITS
    erah
    0.08
    θμ
    0.07
     foreseeable
    0.07
     gibi
    0.07
    Ğ
    0.07
    ایع
    0.07
     minimal
    0.07
     موقع
    0.07
    _mr
    0.06
     hefty
    0.06
    Act Density 0.017%

    No Known Activations