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

    Neuronpedia

    INDEX
    Explanations

    past tense verbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     relegated
    -0.07
    óa
    -0.06
    =((
    -0.06
    _x
    -0.06
    	str
    -0.06
    -0.06
    lings
    -0.06
     华
    -0.06
    	max
    -0.06
    abaj
    -0.06
    POSITIVE LOGITS
     chúng
    0.07
     intention
    0.07
     adapting
    0.07
     obsession
    0.06
    なら
    0.06
    heard
    0.06
    غان
    0.06
     tarn
    0.06
     سالم
    0.06
    EXIST
    0.06
    Act Density 0.037%

    No Known Activations