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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Funny
    -0.06
     inoc
    -0.06
    jud
    -0.06
     Ve
    -0.06
     paddingHorizontal
    -0.06
    };
    -0.06
     Ví
    -0.06
    .Throw
    -0.06
     Rider
    -0.06
    Vars
    -0.06
    POSITIVE LOGITS
    альну
    0.07
    _emp
    0.07
    sent
    0.07
    领导
    0.06
    ühl
    0.06
    discount
    0.06
    اون
    0.06
    elle
    0.06
     семей
    0.06
     IData
    0.06
    Act Density 0.010%

    No Known Activations