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

    Neuronpedia

    INDEX
    Explanations

    greentext style, need/want

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fellow
    0.73
    팰
    0.65
    աշ
    0.65
     puzzle
    0.65
    ומ
    0.64
     tightly
    0.62
    től
    0.60
     cumulative
    0.59
     terminating
    0.59
    ణాలు
    0.59
    POSITIVE LOGITS
     bisogno
    0.60
     اريد
    0.59
    DVRIP
    0.59
     zei
    0.57
    กระท
    0.56
    MH
    0.55
     nevoie
    0.55
     extraño
    0.55
     jakieś
    0.55
     rekao
    0.55
    Act Density 0.014%

    No Known Activations