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

    Neuronpedia

    INDEX
    Explanations

    remarkable development and expansion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    。
    0.96
    *.
    0.82
    ).
    0.80
    ®.
    0.76
    .
    0.76
    %.
    0.75
    ™.
    0.74
    ].
    0.72
    }.
    0.70
    _.
    0.70
    POSITIVE LOGITS
    했고
    1.08
     없고
    1.02
    었고
    0.89
     있으며
    0.80
     এবং
    0.77
     และ
    0.77
     있고
    0.76
     ਅਤੇ
    0.74
     and
    0.72
     और
    0.71
    Act Density 0.172%

    No Known Activations