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

    Neuronpedia

    INDEX
    Explanations

    punctuation and phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    კო
    0.45
     Lou
    0.44
    Lou
    0.43
    CJK
    0.41
     Jenny
    0.39
    Jenny
    0.39
     tempo
    0.39
     tendered
    0.38
    तुम्हारा
    0.37
     context
    0.37
    POSITIVE LOGITS
     მან
    0.38
    klär
    0.37
     onChanged
    0.37
     سنج
    0.36
    bullet
    0.36
     المحاضره
    0.36
    钤
    0.36
     অনন্ত
    0.36
    arlık
    0.35
    何度も
    0.34
    Act Density 0.000%

    No Known Activations