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

    Neuronpedia

    INDEX
    Explanations

    code and structured lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wearer
    0.40
     gerne
    0.38
    ->"
    0.38
    ెం
    0.37
    会员
    0.37
    વણી
    0.37
     ."
    0.36
    眎
    0.36
    }^{-}
    0.36
    стор
    0.36
    POSITIVE LOGITS
    )]);
    0.48
     dilap
    0.38
    )]),
    0.38
    ])):
    0.37
     inputted
    0.37
    oplanes
    0.36
     testified
    0.36
    ))),
    0.36
     cultures
    0.34
     inhibiting
    0.34
    Act Density 0.017%

    No Known Activations