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

    Neuronpedia

    INDEX
    Explanations

    Code and software development

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =W
    -0.08
    REPORT
    -0.07
     version
    -0.07
    WARNING
    -0.07
     dialogue
    -0.07
     "*
    -0.06
    patients
    -0.06
    ];
↵
    -0.06
     유저
    -0.06
     colony
    -0.06
    POSITIVE LOGITS
    医院
    0.06
    لاث
    0.06
    тор
    0.06
    _proto
    0.06
    objc
    0.06
    ají
    0.06
     pornofilm
    0.06
    .btn
    0.06
    _Inter
    0.05
    .TextInput
    0.05
    Act Density 0.054%

    No Known Activations