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

    Neuronpedia

    INDEX
    Explanations

    engine horsepower

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Immobilien
    0.64
     Bedürfn
    0.63
     Refs
    0.62
     Once
    0.61
    터
    0.60
     Tổng
    0.59
     Tử
    0.59
     Ciencias
    0.58
     Ciências
    0.57
     Indices
    0.57
    POSITIVE LOGITS
     to
    0.79
    AK
    0.71
     auch
    0.68
    2
    0.67
     ook
    0.66
    AKE
    0.65
     a
    0.64
     i
    0.64
     se
    0.62
     ab
    0.62
    Act Density 0.000%

    No Known Activations