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

    Neuronpedia

    INDEX
    Explanations

    Tesla

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    chaft
    -0.07
     Evrop
    -0.06
     бед
    -0.06
     Brett
    -0.06
    .plot
    -0.06
     Bret
    -0.06
    疾
    -0.06
     Jorge
    -0.06
     antigen
    -0.06
     mant
    -0.06
    POSITIVE LOGITS
     Tesla
    0.17
    Tesla
    0.14
    )!=
    0.07
    (nc
    0.07
     Pelosi
    0.07
     SpaceX
    0.07
     Recycling
    0.06
    terrorism
    0.06
    Tau
    0.06
    "])
    0.06
    Act Density 0.001%

    No Known Activations