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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    !/
    -0.07
    phalt
    -0.06
    DataSource
    -0.06
    _m
    -0.06
    _esc
    -0.06
    組織
    -0.06
    .dao
    -0.06
    Join
    -0.06
    /watch
    -0.06
    _fire
    -0.06
    POSITIVE LOGITS
    before
    0.07
    .scalablytyped
    0.06
     СП
    0.06
    .note
    0.06
    erald
    0.06
    蘭
    0.06
    \Php
    0.06
    <?
    0.06
     выраж
    0.06
     gran
    0.06
    Act Density 0.023%

    No Known Activations