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

    Neuronpedia

    INDEX
    Explanations

    descriptive and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ProductName
    0.53
     Consc
    0.48
     Synd
    0.48
     Pray
    0.46
     Lifestyle
    0.46
     provoke
    0.46
     aspire
    0.46
     mankind
    0.44
     provoking
    0.44
    磴
    0.44
    POSITIVE LOGITS
    eper
    0.46
    omely
    0.46
    er
    0.44
    daten
    0.44
    berg
    0.44
    ക്കുറ
    0.42
    Alo
    0.42
    thermal
    0.41
    *
    0.41
    akumar
    0.41
    Act Density 0.002%

    No Known Activations