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

    Neuronpedia

    INDEX
    Explanations

    social contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ্যাক
    2.32
    ໍ່
    2.24
    육
    2.19
    avec
    2.14
    ậy
    2.08
    ąg
    2.08
     stod
    2.07
    ='%
    2.05
    丂
    2.05
    urne
    2.05
    POSITIVE LOGITS
    कुंठ
    3.11
    esine
    2.87
    ا
    2.84
    ed
    2.83
    hala
    2.81
    naires
    2.81
    alysis
    2.81
    ের
    2.79
    angements
    2.75
    h
    2.71
    Act Density 1.069%

    No Known Activations