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

    Neuronpedia

    INDEX
    Explanations

    mathematical operations or code segments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ControlEvents
    0.40
    Hayes
    0.38
    Cpp
    0.38
    ounds
    0.36
     chão
    0.36
     колеба
    0.36
     бога
    0.35
    Chorus
    0.35
    кина
    0.35
    柴
    0.35
    POSITIVE LOGITS
     comp
    0.42
     wre
    0.39
    ో
    0.39
     mum
    0.39
     tie
    0.39
     playful
    0.38
     lo
    0.38
     FAC
    0.37
    쓸
    0.37
     exporting
    0.37
    Act Density 0.011%

    No Known Activations