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

    Neuronpedia

    INDEX
    Explanations

    Foreign languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SpaceItem
    -0.06
    技能
    -0.06
    _EV
    -0.06
     what
    -0.06
     Management
    -0.06
     رع
    -0.05
     Dien
    -0.05
     when
    -0.05
     botanical
    -0.05
    messages
    -0.05
    POSITIVE LOGITS
    очка
    0.10
    inha
    0.07
    っき
    0.07
    очку
    0.07
    chen
    0.07
    ="↵
    0.07
    alg
    0.07
    ści
    0.07
    yat
    0.07
     louis
    0.07
    Act Density 0.073%

    No Known Activations