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

    Neuronpedia

    INDEX
    Explanations

    time words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ù
    -0.08
    WATCH
    -0.06
    ampton
    -0.06
    <UnityEngine
    -0.06
     Pharmacy
    -0.06
     Gwen
    -0.06
    _solve
    -0.06
     draws
    -0.06
    _cs
    -0.06
     PACK
    -0.06
    POSITIVE LOGITS
    ез
    0.08
    (actor
    0.07
    тесь
    0.07
    aciones
    0.07
     Alg
    0.07
    	rb
    0.06
    ,target
    0.06
    Actor
    0.06
     väl
    0.06
    的な
    0.06
    Act Density 0.032%

    No Known Activations