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

    Neuronpedia

    INDEX
    Explanations

    technical

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wicht
    -0.07
    ltr
    -0.07
    implement
    -0.07
    .Touch
    -0.07
     shar
    -0.06
     火
    -0.06
    ská
    -0.06
    ủy
    -0.06
     BitConverter
    -0.06
     kingdoms
    -0.06
    POSITIVE LOGITS
    $options
    0.08
     
    0.07
     GENERAL
    0.07
    itated
    0.07
     clauses
    0.06
     plumbing
    0.06
    (hostname
    0.06
     trusting
    0.06
     directs
    0.06
    getTitle
    0.06
    Act Density 0.269%

    No Known Activations