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

    Neuronpedia

    INDEX
    Explanations

    changed names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Windsor
    -0.07
    -changing
    -0.07
    ForRow
    -0.07
     fas
    -0.06
     Clause
    -0.06
     çıkış
    -0.06
    .Manifest
    -0.06
    _None
    -0.06
    Expert
    -0.06
     paramount
    -0.06
    POSITIVE LOGITS
    ną
    0.06
    兽
    0.06
    вер
    0.06
     theft
    0.06
     past
    0.06
     Liu
    0.06
    +'.
    0.06
     zastav
    0.06
    luck
    0.06
     nä
    0.06
    Act Density 0.014%

    No Known Activations