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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     $\%
    0.38
    :":
    0.37
    🚞
    0.36
    هما
    0.36
    फिकेशन
    0.35
     $\%$
    0.34
    kyverno
    0.34
    hiqdev
    0.34
    ቀት
    0.33
    libexec
    0.33
    POSITIVE LOGITS
     ≥
    0.54
     ≤
    0.52
     δ
    0.48
    <sub>
    0.47
     ∈
    0.46
     β
    0.46
     ε
    0.45
     ψ
    0.44
     ≠
    0.44
     σ
    0.44
    Act Density 0.212%

    No Known Activations