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

    Neuronpedia

    INDEX
    Explanations

    generally, typically, what's happening

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ☺
    0.42
    😃
    0.40
    teryx
    0.39
     Woo
    0.38
     🙂
    0.38
     Mould
    0.38
    秩
    0.38
     ;)
    0.38
    MOV
    0.37
     Aspir
    0.37
    POSITIVE LOGITS
     Jana
    0.50
    судар
    0.48
    怜
    0.44
     geralmente
    0.41
     generally
    0.40
    esar
    0.38
     generalmente
    0.37
     typically
    0.37
     সেক্রে
    0.36
     ጉዳ
    0.36
    Act Density 0.001%

    No Known Activations