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

    Neuronpedia

    INDEX
    Explanations

    informational texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     the
    -0.10
     The
    -0.09
    The
    -0.08
     의
    -0.07
     At
    -0.07
     la
    -0.07
    �
    -0.07
     город
    -0.07
    ріп
    -0.07
     Of
    -0.07
    POSITIVE LOGITS
    -placeholder
    0.07
    -hero
    0.06
    (exception
    0.06
     orta
    0.06
    removeClass
    0.06
     mutlu
    0.06
     measles
    0.06
     Nẵng
    0.05
    _trajectory
    0.05
     lon
    0.05
    Act Density 3.463%

    No Known Activations