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

    Neuronpedia

    INDEX
    Explanations

    programming constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kajian
    0.49
    reducible
    0.46
    員の
    0.45
    ];
    0.45
    𝘳
    0.45
     alternatif
    0.45
    पीरियंस
    0.45
     agonist
    0.44
     possibili
    0.44
    言って
    0.44
    POSITIVE LOGITS
     Too
    0.51
    ator
    0.48
    lando
    0.47
     Poor
    0.47
    apa
    0.46
    .
    0.45
     too
    0.43
    ack
    0.43
    anges
    0.42
    aria
    0.42
    Act Density 0.016%

    No Known Activations