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

    Neuronpedia

    INDEX
    Explanations

    explaining why

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     zde
    0.46
     frmt
    0.43
    idane
    0.42
     alternatively
    0.41
    SHE
    0.41
     vini
    0.41
    υ
    0.41
    ely
    0.41
     pts
    0.40
    SS
    0.40
    POSITIVE LOGITS
     напомина
    0.46
     queer
    0.45
     напом
    0.44
     ก็
    0.44
    📢
    0.43
     народ
    0.42
     nationalist
    0.42
     दोन्ही
    0.42
     अक्सर
    0.42
     потенциа
    0.42
    Act Density 0.014%

    No Known Activations