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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, code, or lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     //#
    0.75
     Wikispecies
    0.73
    abhave
    0.72
    .??"]
    0.71
    nvim
    0.69
    <unused527>
    0.68
    твра
    0.68
    ZF
    0.67
    <unused393>
    0.67
     cier
    0.65
    POSITIVE LOGITS
     उनको
    0.84
     Them
    0.81
     Ours
    0.79
     Critical
    0.78
     Damn
    0.76
     They
    0.76
     Their
    0.75
     Our
    0.74
     Except
    0.74
     People
    0.73
    Act Density 0.008%

    No Known Activations