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

    Neuronpedia

    INDEX
    Explanations

    explaining fashion and technical issues

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    राधना
    0.50
    smöglichkeiten
    0.40
     cujo
    0.39
    jk
    0.38
    теру
    0.38
    ukai
    0.37
    силання
    0.37
     proclam
    0.37
     कांड
    0.37
    Ciao
    0.37
    POSITIVE LOGITS
    dress
    0.42
     Pete
    0.41
    በ
    0.39
    Dress
    0.39
    Pete
    0.39
    作为
    0.39
    ব্য
    0.38
     dresser
    0.37
    に
    0.37
    ্র
    0.37
    Act Density 0.000%

    No Known Activations