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

    Neuronpedia

    INDEX
    Explanations

    assign to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vred
    0.50
     dr
    0.49
     Citi
    0.49
     san
    0.47
     Fong
    0.47
     Zhao
    0.46
     Police
    0.46
     siis
    0.45
     Wendy
    0.45
     Delegation
    0.44
    POSITIVE LOGITS
    нти
    0.49
    Lengths
    0.47
    can
    0.46
    revolutionary
    0.45
    assign
    0.44
    埥
    0.44
    음
    0.43
    ंट
    0.43
     octahedral
    0.43
    False
    0.42
    Act Density 0.006%

    No Known Activations