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

    Neuronpedia

    INDEX
    Explanations

    product listing descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bootstrap
    0.55
     Bootstrap
    0.54
     bootstra
    0.51
     bootstrapping
    0.50
    Bootstrap
    0.41
    iguously
    0.40
    BOOT
    0.40
     Boot
    0.39
     Wessex
    0.39
     Zweiten
    0.38
    POSITIVE LOGITS
    🥶
    0.39
    listing
    0.38
     منہ
    0.38
    Captcha
    0.37
    sensors
    0.37
    sensing
    0.37
     शुर
    0.37
    opener
    0.37
     welcoming
    0.35
    бек
    0.35
    Act Density 0.009%

    No Known Activations