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

    Neuronpedia

    INDEX
    Explanations

    direct calls to action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ร่าง
    0.48
     उपकरण
    0.44
     церков
    0.44
     вър
    0.43
     oxalate
    0.41
     admissibility
    0.41
     rope
    0.41
     decomposed
    0.40
     وخ
    0.39
     consequential
    0.39
    POSITIVE LOGITS
     Putri
    0.50
    teki
    0.50
    iril
    0.47
    iris
    0.46
     FILTER
    0.46
    in
    0.45
    i
    0.45
     orientado
    0.44
     orient
    0.44
    ي
    0.44
    Act Density 0.000%

    No Known Activations