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

    Neuronpedia

    INDEX
    Explanations

    special symbol followed by The

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ಗೌ
    0.43
    <unused1726>
    0.41
    aping
    0.41
    ímos
    0.40
    jz
    0.40
    舸
    0.38
     menores
    0.38
    tait
    0.38
    }={
    0.38
     कैफ
    0.37
    POSITIVE LOGITS
    bete
    0.41
     Dick
    0.39
     Dye
    0.38
     Paradise
    0.37
     Sod
    0.37
     Demokrat
    0.37
     উড়িয়ে
    0.37
     Mana
    0.37
     PAR
    0.36
     Te
    0.36
    Act Density 0.000%

    No Known Activations