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

    Neuronpedia

    INDEX
    Explanations

    say "2"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -template
    -0.07
    品质
    -0.07
     Irish
    -0.07
     fresh
    -0.07
     porter
    -0.07
     Famous
    -0.07
     casual
    -0.06
     amateur
    -0.06
    cellent
    -0.06
     precedent
    -0.06
    POSITIVE LOGITS
    �
    0.08
    מלחמת
    0.07
    .exe
    0.07
    ㏊
    0.07
    (robot
    0.07
    (';
    0.07
    兩
    0.07
    风机
    0.07
    (jsonPath
    0.07
     который
    0.07
    Act Density 0.004%

    No Known Activations