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

    Neuronpedia

    INDEX
    Explanations

    potentially even

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    You
    0.48
    Unable
    0.48
     implies
    0.48
     implication
    0.47
     Якщо
    0.47
    4
    0.47
     summarised
    0.46
     customised
    0.45
     emphasises
    0.45
     consequent
    0.44
    POSITIVE LOGITS
     momentos
    0.47
     aerosol
    0.45
     ent
    0.44
     Aram
    0.42
    成為
    0.41
     Dada
    0.41
    硋
    0.41
     espont
    0.40
    adería
    0.40
     arred
    0.39
    Act Density 0.004%

    No Known Activations