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

    Neuronpedia

    INDEX
    Explanations

    the letter F

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     matemático
    0.42
    ildir
    0.40
    Oct
    0.37
    nger
    0.37
     Elig
    0.36
     Oct
    0.36
     Expand
    0.36
    araf
    0.35
     negated
    0.35
     FK
    0.35
    POSITIVE LOGITS
    㝅
    0.38
     रो
    0.37
     राष्ट्रवादी
    0.37
     bedroom
    0.37
    inesi
    0.37
    скай
    0.36
    iseks
    0.36
    해주세요
    0.36
     ಪರಿ
    0.36
     ಕ್ರಮ
    0.36
    Act Density 0.001%

    No Known Activations