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

    Neuronpedia

    INDEX
    Explanations

    the, commas

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.07
     Policy
    -0.07
    iper
    -0.07
     compartments
    -0.07
     highways
    -0.06
    let
    -0.06
     policy
    -0.06
    orph
    -0.06
    -transparent
    -0.06
    /internal
    -0.06
    POSITIVE LOGITS
     Μον
    0.07
    WL
    0.07
    .ToDateTime
    0.06
    <num
    0.06
     Essentials
    0.06
    泰
    0.06
    (curr
    0.06
     adul
    0.06
    oleans
    0.06
    روت
    0.06
    Act Density 0.049%

    No Known Activations