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

    Neuronpedia

    INDEX
    Explanations

    introducing examples or assumptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oble
    0.41
    近年来
    0.39
    Documentation
    0.38
    也不能
    0.38
    注意事项
    0.37
     zuvor
    0.37
    Assembly
    0.35
     benötigt
    0.35
     benötigen
    0.35
    Daten
    0.34
    POSITIVE LOGITS
     assume
    0.64
    assume
    0.59
     simplicity
    0.54
     Assume
    0.52
    Assume
    0.50
     assumed
    0.48
     simpl
    0.46
     simplify
    0.46
     defaulted
    0.45
     simplic
    0.44
    Act Density 0.001%

    No Known Activations