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

    Neuronpedia

    INDEX
    Explanations

    concepts followed by states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     통해
    0.22
     настройки
    0.22
     असून
    0.21
    力和
    0.21
     renaming
    0.21
     صہیونیوں
    0.20
     من
    0.20
     récupération
    0.20
     With
    0.20
     with
    0.20
    POSITIVE LOGITS
     is
    0.34
    are
    0.33
     has
    0.31
     are
    0.31
    is
    0.30
     became
    0.29
     είναι
    0.29
     will
    0.29
     becomes
    0.28
     adalah
    0.27
    Act Density 0.478%

    No Known Activations