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

    Neuronpedia

    INDEX
    Explanations

    this

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Statement
    -0.07
    '<
    -0.06
    ELCOME
    -0.06
    ของค
    -0.06
     borough
    -0.06
    -N
    -0.06
     kurulan
    -0.06
     Av
    -0.06
    ![
    -0.06
     REGISTER
    -0.05
    POSITIVE LOGITS
    ứa
    0.08
     참
    0.07
     každ
    0.07
    ToolBar
    0.07
     Čes
    0.07
     آذ
    0.07
     žal
    0.06
    _AUD
    0.06
    كان
    0.06
    олот
    0.06
    Act Density 0.005%

    No Known Activations