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

    Neuronpedia

    INDEX
    Explanations

    automotive services

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     recipe
    -0.07
    friendly
    -0.06
     Tec
    -0.06
    _LINK
    -0.06
    _TOOL
    -0.06
     ανα
    -0.06
     справ
    -0.06
     Nintendo
    -0.06
     teil
    -0.06
    Roll
    -0.05
    POSITIVE LOGITS
     inclination
    0.07
     ActionTypes
    0.07
     ++)↵
    0.07
    ).(
    0.06
     CSR
    0.06
     پاورپوینت
    0.06
    CCR
    0.06
    FullName
    0.06
    اید
    0.06
    кие
    0.06
    Act Density 0.011%

    No Known Activations