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

    Neuronpedia

    INDEX
    Explanations

    3070 Ti, tonkatsu, Love

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     the
    0.55
    n
    0.54
    y
    0.52
     a
    0.52
    c
    0.50
     an
    0.46
     The
    0.44
    ي
    0.44
     Gruber
    0.42
     Swami
    0.42
    POSITIVE LOGITS
    এবং
    0.52
    ienna
    0.48
     necessitating
    0.46
    ®,
    0.46
     tornando
    0.45
    ™,
    0.44
    ທີ່
    0.44
    न्ग
    0.44
     stronghold
    0.43
     ಮತ್ತು
    0.43
    Act Density 0.066%

    No Known Activations