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

    Neuronpedia

    INDEX
    Explanations

    gun

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    BH
    -0.07
     grounds
    -0.07
    lobber
    -0.07
     ops
    -0.06
    Badge
    -0.06
     Handles
    -0.06
     lucky
    -0.06
     expectation
    -0.06
     DOT
    -0.06
     IDs
    -0.06
    POSITIVE LOGITS
     mặc
    0.06
     metod
    0.06
    Stephen
    0.06
    140
    0.06
    adan
    0.06
     を
    0.06
    parameter
    0.06
    适
    0.06
     свій
    0.06
     natur
    0.06
    Act Density 0.011%

    No Known Activations