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

    Neuronpedia

    INDEX
    Explanations

    (true

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Domains
    -0.07
     Rooms
    -0.07
     envelop
    -0.07
     weer
    -0.06
    _Manager
    -0.06
     sample
    -0.06
     Geek
    -0.06
     необходим
    -0.06
    RANDOM
    -0.06
    RL
    -0.06
    POSITIVE LOGITS
    (true
    0.09
     MaterialApp
    0.07
     isActive
    0.07
    arranty
    0.07
     آلة
    0.07
    ें↵↵
    0.07
     outreach
    0.06
    _tcb
    0.06
    证
    0.06
     */
↵
    0.06
    Act Density 0.001%

    No Known Activations