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

    Neuronpedia

    INDEX
    Explanations

    Ben

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Nar
    -0.07
    SUB
    -0.07
    �
    -0.06
     Fridays
    -0.06
    notify
    -0.06
     copper
    -0.06
     Footer
    -0.06
     Night
    -0.06
    adastrar
    -0.06
     kuvvet
    -0.06
    POSITIVE LOGITS
     discour
    0.06
    重要
    0.06
     자연
    0.06
     раді
    0.06
    reno
    0.06
     conce
    0.06
    かわ
    0.06
     cose
    0.06
    ाव
    0.06
    -import
    0.06
    Act Density 0.002%

    No Known Activations