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

    Neuronpedia

    INDEX
    Explanations

    A

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -ro
    -0.07
     HEALTH
    -0.07
    _prof
    -0.07
     extremism
    -0.06
    _ro
    -0.06
     bod
    -0.06
    _conn
    -0.06
    ̀
    -0.06
     ten
    -0.06
     emploi
    -0.06
    POSITIVE LOGITS
     Komm
    0.06
    独立
    0.06
     yatırım
    0.06
     ビ
    0.06
    .Media
    0.06
     moden
    0.06
    ynchron
    0.06
    tabl
    0.06
    ())
↵
↵
    0.06
    0.05
    Act Density 0.002%

    No Known Activations