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

    Neuronpedia

    INDEX
    Explanations

    innovation and groups

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     практически
    0.38
    anie
    0.37
    ANCE
    0.37
    ឺ
    0.37
    ance
    0.36
    any
    0.36
    Favor
    0.36
    eno
    0.35
    champion
    0.35
    Organ
    0.35
    POSITIVE LOGITS
     موبائل
    0.40
     موب
    0.38
     Quels
    0.38
    蒉
    0.38
    苛
    0.37
     sulphate
    0.37
     MOBILE
    0.37
     Dining
    0.37
    _{+}-
    0.37
     popOperand
    0.37
    Act Density 0.000%

    No Known Activations