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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     updater
    -0.07
    onse
    -0.07
     retaliation
    -0.06
     strugg
    -0.06
     Dust
    -0.06
     confidentiality
    -0.06
    �
    -0.06
     Heather
    -0.06
    ===========↵
    -0.06
    _RANK
    -0.06
    POSITIVE LOGITS
     aime
    0.06
     humorous
    0.06
    ')(
    0.06
     Navy
    0.06
    ?$
    0.06
    ,...
    0.06
    _)
    0.06
    .Editor
    0.06
     They
    0.06
    *&
    0.06
    Act Density 0.023%

    No Known Activations