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

    Neuronpedia

    INDEX
    Explanations

    distinguish

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    RF
    -0.08
    _parsed
    -0.07
     Volvo
    -0.07
    -flow
    -0.07
    /Peak
    -0.07
    adata
    -0.07
     core
    -0.07
    empo
    -0.07
    pv
    -0.07
     jej
    -0.06
    POSITIVE LOGITS
     distinguish
    0.12
     distinguished
    0.11
     distinguishing
    0.10
    istinguished
    0.09
     distinction
    0.08
     distinctions
    0.07
    翰
    0.07
    istingu
    0.07
     отлич
    0.07
     благ
    0.07
    Act Density 0.009%

    No Known Activations