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

    Neuronpedia

    INDEX
    Explanations

    locations, speakers, and browsing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    عات
    0.45
    стым
    0.42
    ⤦
    0.42
    0.42
    以來
    0.41
    менова
    0.41
     newspap
    0.40
    ⭒
    0.40
     currants
    0.40
     anthracite
    0.40
    POSITIVE LOGITS
     BFF
    0.52
     John
    0.48
     Also
    0.48
     BTW
    0.48
     BBQ
    0.47
     También
    0.46
     Evaluation
    0.46
     Emails
    0.46
     GitHub
    0.46
     Também
    0.45
    Act Density 0.001%

    No Known Activations