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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ))
↵
    -0.07
    Fear
    -0.06
    _:*
    -0.06
    obile
    -0.06
     MacOS
    -0.06
     mama
    -0.06
    	hash
    -0.06
    ประก
    -0.06
    增加
    -0.06
     Label
    -0.06
    POSITIVE LOGITS
    /groups
    0.07
     paraph
    0.07
    warts
    0.07
    ởi
    0.07
    Regarding
    0.06
     mustard
    0.06
    VRT
    0.06
     mentions
    0.06
    .mybatis
    0.06
    ْن
    0.06
    Act Density 0.006%

    No Known Activations