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

    Neuronpedia

    INDEX
    Explanations

    numbers in the 420s

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     granny
    -0.08
     nearer
    -0.07
     Emin
    -0.07
     Homer
    -0.07
     Verify
    -0.07
     rer
    -0.07
    get
    -0.07
    edula
    -0.07
    Get
    -0.07
    Owner
    -0.07
    POSITIVE LOGITS
    210
    0.09
    42
    0.08
    :
    0.08
    ו
    0.08
    421
    0.08
    420
    0.07
    211
    0.07
     Silva
    0.07
    vell
    0.07
     cảnh
    0.07
    Act Density 0.084%

    No Known Activations