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

    Neuronpedia

    INDEX
    Explanations

    party

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ội
    -0.07
     öld
    -0.07
     servisi
    -0.07
    엘
    -0.06
    \File
    -0.06
    ्रब
    -0.06
     işlet
    -0.06
     ero
    -0.06
    ril
    -0.06
    tokenizer
    -0.06
    POSITIVE LOGITS
    -party
    0.08
    achable
    0.07
    _Price
    0.07
    .My
    0.07
     Bahamas
    0.07
    .Bundle
    0.06
    /P
    0.06
    .Our
    0.06
    ноп
    0.06
     VIP
    0.06
    Act Density 0.005%

    No Known Activations