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

    Neuronpedia

    INDEX
    Explanations

    return

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ?a
    -0.07
    Wave
    -0.06
     відповідно
    -0.06
    -line
    -0.06
    とも
    -0.06
    -git
    -0.06
     فران
    -0.06
    团
    -0.06
    เอ
    -0.06
    itan
    -0.06
    POSITIVE LOGITS
     >::
    0.06
     friendships
    0.06
    .DataGridViewContentAlignment
    0.06
     pojištění
    0.06
     majet
    0.06
    èmes
    0.06
    esser
    0.06
     componentDidUpdate
    0.06
     ITER
    0.06
     shortcomings
    0.06
    Act Density 0.003%

    No Known Activations