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

    Neuronpedia

    INDEX
    Explanations

    research articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    :
    -0.07
    晴
    -0.06
     H
    -0.06
    Ram
    -0.06
     Clare
    -0.06
     MIS
    -0.06
    과정
    -0.06
     mating
    -0.06
    :-
    -0.06
     IH
    -0.06
    POSITIVE LOGITS
    oningen
    0.07
     conquered
    0.07
    _SL
    0.06
    ]!=
    0.06
    คโน
    0.06
    [column
    0.06
    datos
    0.06
    tering
    0.06
    '=>$_
    0.06
     accents
    0.06
    Act Density 0.054%

    No Known Activations