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

    Neuronpedia

    INDEX
    Explanations

    Punctuation marks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     detector
    -0.07
     detectors
    -0.07
     Delivery
    -0.07
    Detection
    -0.07
    Histogram
    -0.07
    (Player
    -0.07
    705
    -0.06
    NETWORK
    -0.06
     verses
    -0.06
     Observation
    -0.06
    POSITIVE LOGITS
    ()?;↵
    0.07
    	Json
    0.07
     θα
    0.07
    .SuppressLint
    0.06
    "is
    0.06
     ισχ
    0.06
    нь
    0.06
    .consumer
    0.06
     cortisol
    0.06
    mayı
    0.06
    Act Density 0.030%

    No Known Activations