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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ervisor
    -0.07
    <Expression
    -0.07
     Story
    -0.07
    ŷ
    -0.07
    -Level
    -0.06
    rix
    -0.06
    Number
    -0.06
     chord
    -0.06
    Registry
    -0.06
    🎪
    -0.06
    POSITIVE LOGITS
     тек
    0.07
     많
    0.07
     предост
    0.06
     가능
    0.06
    禁忌
    0.06
    do
    0.06
    岳阳
    0.06
    .rand
    0.06
    灵动
    0.06
     brought
    0.06
    Act Density 0.000%

    No Known Activations