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

    Neuronpedia

    INDEX
    Explanations

    effectiveness, explosive, activation, food

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     فقد
    1.32
    śmy
    1.29
    dados
    1.24
    ه
    1.21
    মায়
    1.13
    л
    1.13
     Quellen
    1.12
     "".
    1.11
    TextImage
    1.10
    Veja
    1.09
    POSITIVE LOGITS
    }?
    1.36
    olding
    1.18
    rection
    1.16
     hoti
    1.16
    जीशन
    1.15
    ution
    1.14
    otomy
    1.14
    ik
    1.13
    uar
    1.12
    vation
    1.10
    Act Density 0.000%

    No Known Activations