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

    Neuronpedia

    INDEX
    Explanations

    ot

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "Some
    -0.06
    imal
    -0.06
    として
    -0.06
    지막
    -0.06
     інтерес
    -0.06
     вив
    -0.06
    positive
    -0.06
     앞
    -0.06
     ensuite
    -0.06
     Tried
    -0.06
    POSITIVE LOGITS
     Point
    0.07
     mixer
    0.06
    .SELECT
    0.06
    NR
    0.06
    องท
    0.06
    \Mail
    0.06
     MCP
    0.06
    .union
    0.06
     Fargo
    0.06
    790
    0.06
    Act Density 0.000%

    No Known Activations