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

    Neuronpedia

    INDEX
    Explanations

    single

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     orderly
    -0.07
    -win
    -0.07
    �
    -0.07
     Zoo
    -0.06
    /*
    -0.06
    ，用
    -0.06
     Indones
    -0.06
    Minnesota
    -0.06
     decreases
    -0.06
     зб
    -0.06
    POSITIVE LOGITS
    (es
    0.06
    _templates
    0.06
    ES
    0.06
    аются
    0.06
     tyre
    0.06
     अब
    0.06
    proposal
    0.06
    .impl
    0.06
     ['$
    0.06
    emem
    0.06
    Act Density 0.012%

    No Known Activations