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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /lgpl
    -0.07
     healer
    -0.06
    itzerland
    -0.06
    ailand
    -0.06
    erialize
    -0.06
    ambique
    -0.06
    Stride
    -0.06
    DeviceInfo
    -0.06
     urč
    -0.06
    rites
    -0.06
    POSITIVE LOGITS
     sigh
    0.10
    ';';
    0.07
    を作
    0.07
    ガ
    0.07
     dokument
    0.06
     COLLECTION
    0.06
     deletes
    0.06
    .deb
    0.06
     potřeb
    0.06
     MethodInfo
    0.06
    Act Density 0.013%

    No Known Activations