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

    Neuronpedia

    INDEX
    Explanations

    it

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    antes
    -0.07
     gratuita
    -0.06
    UIT
    -0.06
     kö
    -0.06
    ılığı
    -0.06
    ลาด
    -0.06
    üc
    -0.06
    uit
    -0.06
     jaw
    -0.06
    .have
    -0.06
    POSITIVE LOGITS
     ㅇㅇ
    0.07
    独
    0.07
     pet
    0.06
    만
    0.06
     validators
    0.06
     microphone
    0.06
    	category
    0.06
     foreclosure
    0.06
     spawning
    0.06
    (DIR
    0.06
    Act Density 0.000%

    No Known Activations