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

    Neuronpedia

    INDEX
    Explanations

    database indexing for performance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IA
    0.53
     pact
    0.50
     entities
    0.50
     purging
    0.49
     पीओ
    0.49
     entity
    0.47
     epicenter
    0.47
    ジェ
    0.47
     bathing
    0.46
     melting
    0.46
    POSITIVE LOGITS
    фер
    0.58
     अशी
    0.58
     Exerc
    0.57
    snp
    0.55
    Glor
    0.55
    ක
    0.54
    മ
    0.54
    лып
    0.53
     Rout
    0.52
     yrs
    0.52
    Act Density 0.014%

    No Known Activations