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

    Neuronpedia

    INDEX
    Explanations

    programming libraries and tools

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Cliffs
    0.44
     Scrub
    0.36
     Hacks
    0.36
    周围
    0.35
    brook
    0.34
     Jerseys
    0.34
    dington
    0.34
     Brentwood
    0.34
     Creek
    0.34
     énorm
    0.34
    POSITIVE LOGITS
     అదే
    0.42
     util
    0.36
    Су
    0.35
    util
    0.34
    I
    0.34
    power
    0.34
     جانا
    0.34
    У
    0.34
     Владими
    0.33
    Работа
    0.33
    Act Density 0.043%

    No Known Activations