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

    Neuronpedia

    INDEX
    Explanations

    Abstract

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    チャ
    -0.06
    Orig
    -0.06
    Portfolio
    -0.06
     IE
    -0.06
    oley
    -0.06
    .LA
    -0.06
    ignum
    -0.06
     QAction
    -0.06
    attrs
    -0.06
     >(
    -0.06
    POSITIVE LOGITS
    :numel
    0.07
     testified
    0.07
     denying
    0.07
     stabbed
    0.06
    フ
    0.06
    Target
    0.06
    กร
    0.06
    lenen
    0.06
    ┴
    0.06
    Without
    0.06
    Act Density 0.002%

    No Known Activations