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

    Neuronpedia

    INDEX
    Explanations

    instructions and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    れる
    -0.07
    所需的
    -0.07
    ﻲ
    -0.07
    .Contains
    -0.07
    erness
    -0.06
     siz
    -0.06
     gibt
    -0.06
    .put
    -0.06
    _Native
    -0.06
    .No
    -0.06
    POSITIVE LOGITS
     капит
    0.07
    tokenId
    0.07
     salvage
    0.07
     Cyrus
    0.07
    皓
    0.06
     prisons
    0.06
     Pharmac
    0.06
     fores
    0.06
    ифика
    0.06
    peria
    0.06
    Act Density 0.010%

    No Known Activations