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

    Neuronpedia

    INDEX
    Explanations

    not

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rf
    -0.06
     Север
    -0.06
    ្�
    -0.06
     pošk
    -0.06
     Anthony
    -0.06
    ,proto
    -0.06
    .Raise
    -0.06
     Sinh
    -0.06
    jišť
    -0.06
     Sunder
    -0.06
    POSITIVE LOGITS
     seized
    0.07
    _COR
    0.07
    MER
    0.07
    liğin
    0.07
    no
    0.07
     shot
    0.07
    ownload
    0.07
     Constitutional
    0.06
    omes
    0.06
     ")
    0.06
    Act Density 0.001%

    No Known Activations