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

    Neuronpedia

    INDEX
    Explanations

    important considerations before you start

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cite
    0.41
     fasci
    0.39
     extrapolated
    0.39
    ائن
    0.38
     ventaja
    0.37
    ∈
    0.37
    excerpt
    0.36
    ⊃
    0.36
     renormalized
    0.35
     स्रोत
    0.34
    POSITIVE LOGITS
    ดาว
    0.45
    default
    0.42
     ดาว
    0.41
     talents
    0.41
     Helper
    0.40
    制作
    0.38
    icons
    0.38
    তিন
    0.37
     Shell
    0.37
     GitHub
    0.37
    Act Density 0.010%

    No Known Activations