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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _DECLARE
    -0.07
    μένη
    -0.07
     Crimes
    -0.06
    ("{\"
    -0.06
     Bah
    -0.06
    Ин
    -0.06
     componentDid
    -0.06
    _PRICE
    -0.06
    illes
    -0.06
     Autism
    -0.06
    POSITIVE LOGITS
    เสร
    0.07
    INGS
    0.07
    .Plugin
    0.06
     abol
    0.06
    (slot
    0.06
     topology
    0.06
     abolish
    0.06
     broadcast
    0.06
     Philippines
    0.06
    (ent
    0.06
    Act Density 0.091%

    No Known Activations