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

    Neuronpedia

    INDEX
    Explanations

    Public places and events

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     παρα
    -0.07
     Victoria
    -0.06
    sequential
    -0.06
     KH
    -0.06
     disadvantages
    -0.06
     우리
    -0.06
     alert
    -0.06
     elder
    -0.06
    Entered
    -0.06
     gym
    -0.06
    POSITIVE LOGITS
    amacare
    0.06
    elial
    0.06
    ##_
    0.06
    istring
    0.06
    warf
    0.06
    SupportFragmentManager
    0.06
     findet
    0.06
    orta
    0.06
    aland
    0.06
    (REG
    0.06
    Act Density 0.022%

    No Known Activations