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

    Neuronpedia

    INDEX
    Explanations

    copyrighted works

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SON
    0.54
    lars
    0.53
    ।
    0.53
    𝐓
    0.53
    ه
    0.52
    AN
    0.52
    এ
    0.52
    COVERY
    0.50
    Inj
    0.50
    }$.
    0.50
    POSITIVE LOGITS
     Na
    0.47
     NA
    0.47
     respectable
    0.47
     incarnations
    0.47
     yere
    0.46
    б
    0.46
     debilitating
    0.45
     sleepless
    0.45
     Mas
    0.44
     teeming
    0.44
    Act Density 0.000%

    No Known Activations