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

    Neuronpedia

    INDEX
    Explanations

    Cryptography

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     outset
    -0.07
     setShow
    -0.07
    _flight
    -0.07
    .Immutable
    -0.06
     searchable
    -0.06
    _stats
    -0.06
    LOOP
    -0.06
     fab
    -0.06
    ception
    -0.06
     Joy
    -0.06
    POSITIVE LOGITS
    (always
    0.06
    ishops
    0.06
    _Ent
    0.06
     Место
    0.06
    くれた
    0.06
    tics
    0.06
    <Link
    0.06
     实
    0.06
     ασ
    0.05
     ná
    0.05
    Act Density 0.027%

    No Known Activations