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

    Neuronpedia

    INDEX
    Explanations

    version

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nj
    0.79
     nh
    0.79
     certainement
    0.76
     langue
    0.75
     pulp
    0.75
     conundrum
    0.73
     fique
    0.71
     εί
    0.70
     mno
    0.70
     kullan
    0.70
    POSITIVE LOGITS
     Member
    0.85
     Provide
    0.83
     Promote
    0.81
     ServiceNow
    0.75
    اً
    0.74
     Minimize
    0.74
    Walmart
    0.74
     Bases
    0.74
     Houses
    0.73
    Provide
    0.73
    Act Density 0.000%

    No Known Activations