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

    Neuronpedia

    INDEX
    Explanations

    formats or statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ZW
    0.50
     каждо
    0.42
    Never
    0.40
    Strat
    0.38
     geograf
    0.38
     ServicePolicy
    0.38
     جدید
    0.38
    Neu
    0.37
    ugawa
    0.37
    :"
    0.37
    POSITIVE LOGITS
     relaxing
    0.42
    ea
    0.40
     payers
    0.39
     ready
    0.39
     inviting
    0.38
     noite
    0.38
     wording
    0.38
     husband
    0.38
     reacts
    0.37
     expecting
    0.37
    Act Density 0.000%

    No Known Activations