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

    Neuronpedia

    INDEX
    Explanations

    particularly

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     doctrine
    -0.07
     jobject
    -0.07
     oznám
    -0.06
    职
    -0.06
    stateParams
    -0.06
    _result
    -0.06
    ::↵
    -0.06
     yana
    -0.06
    $response
    -0.06
    対
    -0.06
    POSITIVE LOGITS
     maturity
    0.07
    ネ
    0.07
     combustion
    0.07
    ster
    0.07
     Ph
    0.07
    .Release
    0.07
    ืน
    0.07
     Espresso
    0.07
     prem
    0.06
     отд
    0.06
    Act Density 0.007%

    No Known Activations