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

    Neuronpedia

    INDEX
    Explanations

    reduce, force, tuition, polynomial

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    call
    0.47
    tiktok
    0.45
    🥳
    0.45
    🥹
    0.42
    queens
    0.42
     ओटी
    0.42
    🫶
    0.42
    🧸
    0.41
    fort
    0.40
    raya
    0.40
    POSITIVE LOGITS
     Willey
    0.43
     DREAM
    0.43
     Huffington
    0.42
    0.41
     rump
    0.41
     হরত
    0.40
     जाधव
    0.40
    ُمْ
    0.40
     informing
    0.39
     allegedly
    0.39
    Act Density 0.000%

    No Known Activations