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

    Neuronpedia

    INDEX
    Explanations

    contextual conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    amodel
    0.42
     শুদ্ধ
    0.40
    гу
    0.38
    Dn
    0.37
     bathtub
    0.35
     fabrics
    0.35
    ভুক্ত
    0.35
    Cardinal
    0.34
     column
    0.34
     Wolf
    0.34
    POSITIVE LOGITS
    viene
    0.39
    acylglycer
    0.39
    濬
    0.38
    encial
    0.38
     comprado
    0.38
     agregado
    0.37
    boe
    0.36
     capacidad
    0.36
     Aaj
    0.36
    ജ
    0.36
    Act Density 0.001%

    No Known Activations