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

    Neuronpedia

    INDEX
    Explanations

    behaviors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fusca
    -0.70
     ſche
    -0.69
     fidélité
    -0.67
     defStyleAttr
    -0.67
    FieldBuilder
    -0.66
     useRouter
    -0.66
    ReusableCell
    -0.65
     faſt
    -0.65
     الحره
    -0.63
     entière
    -0.62
    POSITIVE LOGITS
     und
    0.51
    ring
    0.50
     required
    0.50
    bau
    0.50
    кономі
    0.49
     and
    0.48
    men
    0.48
     cast
    0.47
    mod
    0.47
     Bau
    0.47
    Act Density 0.039%

    No Known Activations