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

    Neuronpedia

    INDEX
    Explanations

    init

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    >Error
    -0.08
    弈
    -0.07
    "http
    -0.07
    닯
    -0.07
    מוסר
    -0.07
    风口
    -0.07
    铽
    -0.07
    傺
    -0.07
    .setFont
    -0.07
    콥
    -0.07
    POSITIVE LOGITS
     formula
    0.08
     Directive
    0.07
    Ư
    0.07
     metadata
    0.07
    affe
    0.07
     Clause
    0.07
     także
    0.07
     Mult
    0.07
     Maths
    0.07
    isiert
    0.07
    Act Density 0.001%

    No Known Activations