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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     KH
    -0.07
     işlem
    -0.06
    Ｃ
    -0.06
    оба
    -0.06
    立て
    -0.06
     cot
    -0.06
    stateParams
    -0.06
    vation
    -0.06
    +z
    -0.06
    convertView
    -0.06
    POSITIVE LOGITS
    sorting
    0.06
     fleet
    0.06
    Unavailable
    0.06
     negligible
    0.06
     beings
    0.06
    ;?>↵
    0.06
     mage
    0.06
    {
↵
↵
    0.06
     deceptive
    0.06
    none
    0.06
    Act Density 0.067%

    No Known Activations