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

    Neuronpedia

    INDEX
    Explanations

    formal language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     faç
    -0.07
    ็กซ
    -0.07
    .Components
    -0.07
     Кол
    -0.07
    _controls
    -0.07
    ét
    -0.06
     antagonist
    -0.06
     hull
    -0.06
    reward
    -0.06
    óm
    -0.06
    POSITIVE LOGITS
     جشن
    0.07
    estation
    0.06
     abducted
    0.06
     استاد
    0.06
    ammu
    0.06
     impressed
    0.06
     jour
    0.05
    otent
    0.05
     depressive
    0.05
     tarihli
    0.05
    Act Density 0.212%

    No Known Activations