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

    Neuronpedia

    INDEX
    Explanations

    numbers after punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ExternalTaskPojo
    0.27
    特朗普
    0.26
    AutoStabilise
    0.26
    Khokhlov
    0.25
    qualiter
    0.25
    ROff
    0.24
    Przyp
    0.24
    Databaze
    0.24
     Règles
    0.24
     Verifica
    0.23
    POSITIVE LOGITS
    0
    0.38
     and
    0.35
    I
    0.32
     be
    0.31
    1
    0.31
     I
    0.28
    5
    0.28
     to
    0.28
     or
    0.27
    2
    0.27
    Act Density 0.187%

    No Known Activations