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

    Neuronpedia

    INDEX
    Explanations

    progress indicators, tree views

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    zón
    0.45
     Company
    0.45
     Compañ
    0.44
     pensioner
    0.43
     Matcha
    0.40
    anda
    0.39
    ம்பெ
    0.38
     Redeem
    0.38
     Serve
    0.38
    കും
    0.38
    POSITIVE LOGITS
    ิต
    0.45
    женности
    0.40
     море
    0.38
    invest
    0.37
    ezing
    0.37
     sweetest
    0.37
    USB
    0.36
    掌握
    0.36
    肝
    0.36
    诿
    0.36
    Act Density 0.006%

    No Known Activations