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

    Neuronpedia

    INDEX
    Explanations

    abdication of throne

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    TestingModule
    -0.07
     belief
    -0.06
     Magnet
    -0.06
    าษ
    -0.06
     '"
    -0.06
    ipherals
    -0.06
     pero
    -0.06
     veh
    -0.06
     invite
    -0.06
    texto
    -0.06
    POSITIVE LOGITS
    应
    0.07
     金
    0.07
     coloc
    0.07
     Jenkins
    0.06
     TMZ
    0.06
     visual
    0.06
    뿐
    0.06
    числ
    0.06
    WARDED
    0.06
    (steps
    0.06
    Act Density 0.005%

    No Known Activations