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

    Neuronpedia

    INDEX
    Explanations

    problem solving steps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    --)
    0.39
    aller
    0.37
     religioso
    0.36
    ুরা
    0.35
     commendable
    0.35
    كلات
    0.35
    arag
    0.34
    Crazy
    0.34
    salad
    0.34
    ردم
    0.34
    POSITIVE LOGITS
    Answer
    0.62
     Answer
    0.59
     Author
    0.43
     Ответ
    0.42
     ANSWER
    0.41
     Steps
    0.40
    Solution
    0.40
    Steps
    0.39
    Step
    0.39
     Sana
    0.39
    Act Density 0.001%

    No Known Activations