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

    Neuronpedia

    INDEX
    Explanations

    transcend, transgress, and form

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     trans
    0.76
     Trans
    0.67
    Trans
    0.66
    trans
    0.66
     TRAN
    0.58
     tran
    0.58
     ट्रांस
    0.56
     TRANS
    0.55
     transmembrane
    0.53
    Tran
    0.53
    POSITIVE LOGITS
    gress
    0.48
     Aktion
    0.47
    formations
    0.46
    gressive
    0.44
    Formation
    0.44
    ᴄ
    0.43
    าค
    0.43
    ference
    0.42
    formation
    0.42
    formed
    0.42
    Act Density 0.003%

    No Known Activations