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

    Neuronpedia

    INDEX
    Explanations

    Raw data/code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tuple
    -0.07
    ]=="
    -0.07
    IMPLIED
    -0.06
     plaint
    -0.06
    以及
    -0.06
     nostro
    -0.06
    <Menu
    -0.06
    .rpm
    -0.06
    놓
    -0.06
    ">-->↵
    -0.06
    POSITIVE LOGITS
     Next
    0.06
     Ferguson
    0.06
    эф
    0.06
    haar
    0.06
     nonexistent
    0.06
    iah
    0.06
     Soup
    0.06
     neredeyse
    0.06
     europ
    0.06
    istema
    0.06
    Act Density 0.000%

    No Known Activations