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

    Neuronpedia

    INDEX
    Explanations

    early or late periods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     December
    0.64
     October
    0.58
     November
    0.55
     dicembre
    0.54
     January
    0.53
    November
    0.53
     octobre
    0.52
     decembrie
    0.52
    October
    0.51
     november
    0.50
    POSITIVE LOGITS
    Drawable
    0.46
     എല്ലാം
    0.40
    ักษณะ
    0.39
     Solidity
    0.39
    唵
    0.39
    BlockUsed
    0.38
    Param
    0.38
    Trait
    0.38
     syllable
    0.38
     ব্যবহার
    0.38
    Act Density 0.062%

    No Known Activations