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

    Neuronpedia

    INDEX
    Explanations

    physical layer, controlled access, perceived performance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ইতিহাস
    0.40
     RTI
    0.39
     Bxb
    0.38
    bol
    0.38
    ativity
    0.38
    טא
    0.38
    മോ
    0.37
    珽
    0.37
     binomial
    0.37
    🎈
    0.37
    POSITIVE LOGITS
     observed
    0.43
     detectable
    0.43
     reversible
    0.42
    reversible
    0.42
     stimulated
    0.42
    stimulating
    0.41
     regelmäßig
    0.41
     measurable
    0.40
     prosper
    0.40
     valuable
    0.39
    Act Density 0.003%

    No Known Activations