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

    Neuronpedia

    INDEX
    Explanations

    method

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    িৎ
    0.43
    Acte
    0.40
    PartOf
    0.39
    ItemLayout
    0.39
    诊断
    0.38
    Nonnull
    0.38
    InitFlag
    0.38
    Communication
    0.37
     अलं
    0.37
     tenu
    0.37
    POSITIVE LOGITS
     direct
    0.89
     traditional
    0.89
     methods
    0.88
     tradizionale
    0.83
     manual
    0.82
     tradicional
    0.81
     simple
    0.79
    傳統
    0.78
     method
    0.78
     Traditional
    0.77
    Act Density 0.131%

    No Known Activations