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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Independent
    -0.07
     Leadership
    -0.06
    HIR
    -0.06
    jest
    -0.06
    ad
    -0.06
    atus
    -0.06
     leadership
    -0.06
     Lobby
    -0.06
     independent
    -0.06
     measurements
    -0.06
    POSITIVE LOGITS
     اس
    0.07
    Features
    0.07
    chyb
    0.07
     slou
    0.07
    sei
    0.06
    '][$
    0.06
    ンプ
    0.06
    _clicked
    0.06
     nitel
    0.06
     acct
    0.06
    Act Density 0.015%

    No Known Activations