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

    Neuronpedia

    INDEX
    Explanations

    Years 197-201

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     merit
    -0.07
     identifiable
    -0.07
     Durham
    -0.06
     offended
    -0.06
     Org
    -0.06
     who
    -0.06
    685
    -0.06
    _moves
    -0.06
    .controller
    -0.06
     Certif
    -0.06
    POSITIVE LOGITS
     относят
    0.06
    cession
    0.06
    κολ
    0.06
    PathComponent
    0.06
    Sleep
    0.06
    .align
    0.06
    ocking
    0.06
     cravings
    0.06
    (JFrame
    0.06
    bruar
    0.06
    Act Density 0.104%

    No Known Activations