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

    Neuronpedia

    INDEX
    Explanations

    heat loss

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    joint
    0.42
    third
    0.42
     Monitor
    0.40
    ções
    0.39
    िब
    0.38
     monitor
    0.38
    Fourier
    0.37
    checker
    0.37
     third
    0.37
    Monitor
    0.37
    POSITIVE LOGITS
     pajama
    0.45
     건
    0.45
    𝖘
    0.40
    ாளர்கள்
    0.38
    _"
    0.38
    мого
    0.38
    ῃ
    0.38
     accompanies
    0.38
    ૢ
    0.37
    ophage
    0.37
    Act Density 0.000%

    No Known Activations