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

    Neuronpedia

    INDEX
    Explanations

    equipment or usage sections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     glycer
    0.24
     neutrinos
    0.24
     benthic
    0.24
     Wochschr
    0.23
     thermally
    0.23
    രുവനന്തപു
    0.23
     diarr
    0.22
     mRNAs
    0.22
     Bayesian
    0.22
     hyperparameters
    0.22
    POSITIVE LOGITS
    ：
    0.49
    :
    0.43
    ő
    0.33
     करें
    0.32
    ња
    0.32
    ↵↵
    0.32
    Ą
    0.32
    ﺎ
    0.31
    б
    0.31
    ៖
    0.31
    Act Density 4.092%

    No Known Activations