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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Wave
    -0.07
     сил
    -0.07
    /name
    -0.06
    (usuario
    -0.06
    vere
    -0.06
     mould
    -0.06
    �
    -0.06
    หร
    -0.06
    θεί
    -0.06
     перший
    -0.06
    POSITIVE LOGITS
    .mi
    0.07
    |/
    0.07
     forgive
    0.07
     prevent
    0.06
    )!↵
    0.06
     battled
    0.06
     unlucky
    0.06
    -strip
    0.06
     knife
    0.06
    itution
    0.06
    Act Density 0.002%

    No Known Activations