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

    Neuronpedia

    INDEX
    Explanations

    "I" at start of sentence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nabíz
    0.64
     closeModal
    0.63
     recieved
    0.62
     خودم
    0.61
     люблю
    0.61
     avevo
    0.60
    ానని
    0.60
     actualizar
    0.59
     currentValue
    0.59
     Blot
    0.59
    POSITIVE LOGITS
    u
    0.76
     or
    0.75
    s
    0.72
    l
    0.70
    c
    0.69
     oder
    0.63
     atau
    0.60
     the
    0.59
    sthe
    0.59
    C
    0.59
    Act Density 0.167%

    No Known Activations