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

    Neuronpedia

    INDEX
    Explanations

    Academic papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    izard
    -0.06
    Attrs
    -0.06
    Refer
    -0.06
     paciente
    -0.06
    Testing
    -0.06
    
    -0.06
     curved
    -0.06
    .titleLabel
    -0.06
     iframe
    -0.06
    _right
    -0.06
    POSITIVE LOGITS
     eyed
    0.07
    ONY
    0.06
     refusing
    0.06
    ,,
    0.06
     ngoài
    0.06
     пром
    0.06
     confirming
    0.06
    {}↵
    0.06
    .mock
    0.06
    egrator
    0.06
    Act Density 0.031%

    No Known Activations