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

    Neuronpedia

    INDEX
    Explanations

    hero section

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ويض
    0.61
    كس
    0.60
    و
    0.60
    ющее
    0.55
    يكون
    0.55
    arquia
    0.55
    زه
    0.54
    طة
    0.54
    ير
    0.54
    都是
    0.53
    POSITIVE LOGITS
     cravings
    0.63
     anticipation
    0.61
     imports
    0.53
     provisions
    0.52
     Vietnamese
    0.52
     nanoscale
    0.52
     orders
    0.52
     ailments
    0.52
     upgrades
    0.51
     oko
    0.50
    Act Density 0.001%

    No Known Activations