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

    Neuronpedia

    INDEX
    Explanations

    were

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    istros
    -0.08
    -agent
    -0.07
     vendor
    -0.07
     memes
    -0.06
    alamat
    -0.06
    -sex
    -0.06
    سین
    -0.06
    :disable
    -0.06
     cans
    -0.06
    Platform
    -0.06
    POSITIVE LOGITS
     Mountain
    0.07
    kul
    0.07
    ovalo
    0.07
     counted
    0.07
    는
    0.07
     turnovers
    0.06
    createForm
    0.06
    --;
    0.06
     FormControl
    0.06
     propio
    0.06
    Act Density 0.000%

    No Known Activations