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

    Neuronpedia

    INDEX
    Explanations

    question marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ="">
↵
    -0.06
    bool
    -0.06
     Best
    -0.06
     INTEGER
    -0.06
    _note
    -0.06
     #:
    -0.06
    ("(%
    -0.06
    Movies
    -0.06
    scenes
    -0.06
     Star
    -0.06
    POSITIVE LOGITS
    ebe
    0.08
     coch
    0.06
     Decom
    0.06
     Thousand
    0.06
     περι
    0.06
     شاهد
    0.06
     shallow
    0.06
     gh
    0.06
    awai
    0.06
     Employee
    0.06
    Act Density 0.039%

    No Known Activations