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

    Neuronpedia

    INDEX
    Explanations

    key features and symptoms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Dancing
    0.72
     corps
    0.67
     unstoppable
    0.64
     dancing
    0.64
     darts
    0.63
     huge
    0.61
     soms
    0.61
     больших
    0.60
     fortunes
    0.60
     fraught
    0.60
    POSITIVE LOGITS
     muhimu
    0.82
    Characteristics
    0.78
    Relevant
    0.76
    relevant
    0.76
     resumen
    0.75
     esenciales
    0.74
    摘要
    0.74
     resumo
    0.73
    ClrBit
    0.71
    сет
    0.71
    Act Density 0.483%

    No Known Activations