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

    Neuronpedia

    INDEX
    Explanations

    ors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    models
    -0.08
    .modal
    -0.07
    .ticket
    -0.07
     inception
    -0.07
    cca
    -0.07
    input
    -0.06
     mur
    -0.06
    goto
    -0.06
    fieldset
    -0.06
    .force
    -0.06
    POSITIVE LOGITS
     FAT
    0.06
     ビ
    0.06
     lavender
    0.06
     GameController
    0.06
     ikea
    0.06
     maior
    0.06
     файла
    0.06
    <IEnumerable
    0.06
     RTWF
    0.06
    ất
    0.06
    Act Density 0.275%

    No Known Activations