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

    Neuronpedia

    INDEX
    Explanations

    political goals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     он
    0.50
     mógł
    0.45
     sẽ
    0.44
     음악
    0.41
    riak
    0.41
     Paul
    0.41
    hör
    0.41
     valv
    0.41
     듣
    0.40
     chỉ
    0.40
    POSITIVE LOGITS
    2
    0.54
    4
    0.52
    ag
    0.51
    Expansion
    0.51
    9
    0.51
    Activation
    0.48
    /
    0.47
    នូវ
    0.47
    CDS
    0.47
    Greeting
    0.47
    Act Density 0.001%

    No Known Activations