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

    Neuronpedia

    INDEX
    Explanations

    more specific descriptive phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Configuration
    0.42
    Lengths
    0.40
     mous
    0.40
    canic
    0.38
    ፈላጊ
    0.38
     நாட்க
    0.37
    绪
    0.37
    勖
    0.37
     autumn
    0.37
    Week
    0.37
    POSITIVE LOGITS
     மது
    0.44
    ほか
    0.39
     NGO
    0.38
     GF
    0.38
    Ǻ
    0.38
     ഗോ
    0.37
     ʼ
    0.36
     ICON
    0.36
     precedents
    0.36
     Patrim
    0.36
    Act Density 0.000%

    No Known Activations