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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .week
    -0.07
    _cb
    -0.06
     продаж
    -0.06
     gall
    -0.06
     Elm
    -0.06
     cleaning
    -0.06
     share
    -0.06
     melting
    -0.06
     Male
    -0.06
    基础
    -0.06
    POSITIVE LOGITS
     populist
    0.07
     unittest
    0.07
    (userData
    0.07
    _DECLARE
    0.07
    ]]);↵
    0.07
    _ARG
    0.07
     sản
    0.07
    return
    0.07
    @register
    0.07
    (mysql
    0.07
    Act Density 0.010%

    No Known Activations