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

    Neuronpedia

    INDEX
    Explanations

    discharge

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     prof
    -0.07
     Tut
    -0.07
     thái
    -0.06
    ontvangst
    -0.06
     Mozart
    -0.06
     nause
    -0.06
     authoritarian
    -0.06
     Seeking
    -0.06
     André
    -0.06
     Franz
    -0.06
    POSITIVE LOGITS
     看
    0.07
    \admin
    0.07
    0.06
     disappoint
    0.06
     shells
    0.06
     tải
    0.06
    """),↵
    0.06
    _MM
    0.06
    เภท
    0.06
     كام
    0.06
    Act Density 0.006%

    No Known Activations