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

    Neuronpedia

    INDEX
    Explanations

    max_length parameter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    graz
    0.34
     personality
    0.31
    za
    0.30
     and
    0.29
     or
    0.29
    state
    0.29
    set
    0.27
    ZA
    0.27
    book
    0.26
    ownership
    0.26
    POSITIVE LOGITS
    DOCKED
    0.34
    Ⲓ
    0.32
     Datos
    0.31
    matmul
    0.31
     líquidos
    0.31
    ಷ್ಯ
    0.31
     viewController
    0.31
    ﮅ
    0.31
     situado
    0.30
     मरम्मत
    0.30
    Act Density 0.004%

    No Known Activations