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

    Neuronpedia

    INDEX
    Explanations

    espionage and secret information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    1.37
    ’
    1.21
     ovvero
    1.20
    ism
    1.08
    r
    1.08
     hubo
    1.07
    K
    1.05
     werd
    1.03
    ’;
    1.02
    s
    1.00
    POSITIVE LOGITS
    اب
    1.27
    ИС
    1.16
    десят
    1.14
    НИЕ
    1.10
    ERA
    1.09
    pras
    1.08
    HING
    1.08
    په
    1.08
    КС
    1.05
    Thriller
    1.05
    Act Density 0.359%

    No Known Activations