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

    Neuronpedia

    INDEX
    Explanations

    quotation marks/apostrophes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sir
    -0.07
     вкус
    -0.07
    afs
    -0.07
    (pdev
    -0.07
    ᵘ
    -0.07
     Tecn
    -0.06
     autofocus
    -0.06
    눗
    -0.06
    YPE
    -0.06
     Gst
    -0.06
    POSITIVE LOGITS
     Rigidbody
    0.07
    .Binary
    0.07
     surgeries
    0.07
     około
    0.07
     posible
    0.06
    ត
    0.06
    不住
    0.06
     disposed
    0.06
    想着
    0.06
     eligible
    0.06
    Act Density 0.002%

    No Known Activations