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

    Neuronpedia

    INDEX
    Explanations

    Walter and Laura names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Zane
    0.50
    銘
    0.44
     illumin
    0.41
    REDIR
    0.40
    *>
    0.38
     मुस्
    0.38
    Obl
    0.37
    づ
    0.37
    Recognition
    0.36
    CLEAR
    0.36
    POSITIVE LOGITS
    loo
    0.38
    डिएट
    0.37
    铛
    0.35
     במה
    0.35
     VIDA
    0.35
     Deere
    0.34
     bremsstrahlung
    0.34
    Sec
    0.34
     Mili
    0.33
    CHD
    0.33
    Act Density 0.009%

    No Known Activations