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

    Neuronpedia

    INDEX
    Explanations

    question and options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kunne
    0.42
     volunteers
    0.42
    schnitt
    0.42
     volunteer
    0.41
     gern
    0.39
     Volunteer
    0.39
     mailing
    0.39
     could
    0.38
     Volunteers
    0.38
    ://
    0.38
    POSITIVE LOGITS
    Question
    0.46
    問
    0.39
    ÉT
    0.39
     Question
    0.39
    WithOptions
    0.39
    뭄
    0.38
    题目
    0.37
    问
    0.37
    eid
    0.36
    求
    0.36
    Act Density 0.003%

    No Known Activations