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

    Neuronpedia

    INDEX
    Explanations

    bash find commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     भाँ
    0.80
     প্রকল্পের
    0.73
     қар
    0.69
    Cannot
    0.69
    കേന്ദ്രം
    0.69
    RegistrationBean
    0.68
     সাংস
    0.68
    鬘
    0.68
    蠡
    0.68
    STAN
    0.68
    POSITIVE LOGITS
     मुलाकात
    0.72
     माइक्रो
    0.65
    day
    0.60
    iche
    0.60
     сх
    0.58
    日に
    0.58
    ilaire
    0.57
    िम
    0.57
     మై
    0.55
     approachable
    0.55
    Act Density 0.003%

    No Known Activations