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

    Neuronpedia

    INDEX
    Explanations

    bright moonlight

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     differences
    0.67
    L
    0.57
    洍
    0.55
     T
    0.54
     L
    0.54
    リ
    0.52
     shortages
    0.52
    M
    0.51
    K
    0.50
    E
    0.50
    POSITIVE LOGITS
    ()
    0.70
     ámbitos
    0.67
    ();
    0.66
     mucha
    0.66
     gaji
    0.66
    ")
    0.66
     किंतु
    0.65
    .
    0.65
     filóso
    0.63
    ')
    0.63
    Act Density 0.973%

    No Known Activations