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

    Neuronpedia

    INDEX
    Explanations

    API Access

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.48
    ikale
    0.45
    OST
    0.44
     Що
    0.44
    O
    0.44
    ash
    0.42
    olik
    0.42
    EH
    0.42
    has
    0.41
    YG
    0.41
    POSITIVE LOGITS
    螂
    0.49
    मध
    0.46
    鱉
    0.46
    鹬
    0.46
    琤
    0.45
     дипло
    0.45
     directors
    0.44
     అర్జు
    0.43
    ୨
    0.42
     oynuyoruz
    0.42
    Act Density 0.000%

    No Known Activations