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

    Neuronpedia

    INDEX
    Explanations

    Up or down movement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Germany
    -0.08
    (||
    -0.07
    currentPage
    -0.07
     webinar
    -0.07
    *.
    -0.07
     استاندارد
    -0.06
    _metrics
    -0.06
    processable
    -0.06
    ová
    -0.06
     Gron
    -0.06
    POSITIVE LOGITS
    _COMPILE
    0.07
    .blog
    0.07
    _DROP
    0.07
     Marxism
    0.06
    take
    0.06
    ">@
    0.06
     πολύ
    0.06
     finns
    0.06
     disappointment
    0.06
    �
    0.06
    Act Density 0.023%

    No Known Activations