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

    Neuronpedia

    INDEX
    Explanations

    approximate numerical values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Philip
    0.43
    λαν
    0.42
    хбет
    0.41
    ल्ली
    0.40
     সাধারণভাবে
    0.40
    =\{\
    0.40
     enmity
    0.39
    ລິ
    0.39
    撩
    0.39
     pomiędzy
    0.38
    POSITIVE LOGITS
     ≈
    0.58
     Appro
    0.47
     appro
    0.46
    Appro
    0.46
    appro
    0.42
     ~
    0.41
     denominations
    0.40
    approx
    0.39
     stof
    0.38
     decimal
    0.38
    Act Density 0.004%

    No Known Activations