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

    Neuronpedia

    INDEX
    Explanations

    organization names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     brillantes
    0.83
     `<`,
    0.80
     suaves
    0.80
     brillant
    0.79
     mollus
    0.79
     corrugated
    0.78
     yeasts
    0.77
     यदि
    0.77
    राइड
    0.76
     tantal
    0.75
    POSITIVE LOGITS
    3
    1.02
    2
    1.00
     originalmente
    0.99
    4
    0.98
    7
    0.95
    SCUS
    0.93
    6
    0.91
    IÓN
    0.84
    อื่น
    0.83
    IU
    0.82
    Act Density 0.418%

    No Known Activations