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

    Neuronpedia

    INDEX
    Explanations

    * incorporated places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ිර
    0.44
    绪
    0.43
     Documents
    0.41
     एटीएम
    0.40
    eventType
    0.40
    材质
    0.40
     സന്തോഷ
    0.40
    ❆
    0.39
     LICENSE
    0.39
     которыми
    0.38
    POSITIVE LOGITS
    ixin
    0.41
     naturally
    0.40
    true
    0.39
     Naturally
    0.38
    supply
    0.37
    Naturally
    0.37
     lament
    0.37
    iche
    0.37
    cone
    0.36
     mant
    0.36
    Act Density 0.001%

    No Known Activations