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

    Neuronpedia

    INDEX
    Explanations

    f-strings and string formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     by
    0.83
     animation
    0.80
    о
    0.80
     injuries
    0.79
    е
    0.79
     about
    0.78
     oscillations
    0.75
     accidents
    0.70
     spasms
    0.70
    skom
    0.70
    POSITIVE LOGITS
    ان
    0.98
    ח
    0.91
    جع
    0.84
    an
    0.83
    Código
    0.79
    يني
    0.77
    method
    0.77
    database
    0.75
    りたい
    0.75
    قليم
    0.75
    Act Density 0.040%

    No Known Activations