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

    Neuronpedia

    INDEX
    Explanations

    collecting and transforming

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pack
    0.40
     bloke
    0.40
     প্রভাস
    0.39
    pack
    0.38
     тик
    0.38
     paket
    0.38
    izo
    0.37
    ético
    0.37
    팩
    0.37
     viewport
    0.36
    POSITIVE LOGITS
     childlike
    0.43
     various
    0.43
    玩具
    0.43
     diy
    0.42
    μφωνα
    0.42
    diy
    0.42
     τὴν
    0.41
    燒
    0.40
    various
    0.40
     ἐ
    0.40
    Act Density 0.001%

    No Known Activations