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

    Neuronpedia

    INDEX
    Explanations

    Sum and product

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    critic
    -0.08
     Hanson
    -0.07
     Aussi
    -0.07
     USE
    -0.07
     predecess
    -0.07
     représentants
    -0.07
    iyana
    -0.07
     FOLLOW
    -0.07
    зык
    -0.07
     IMM
    -0.07
    POSITIVE LOGITS
     confirms
    0.09
     confirming
    0.09
     confirmação
    0.09
    Confirmed
    0.09
     подходят
    0.08
    合わせ
    0.08
     confirmar
    0.08
    确认
    0.08
     bestätigt
    0.08
     توافق
    0.08
    Act Density 0.079%

    No Known Activations