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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dessert
    -0.06
    _vp
    -0.06
    _Record
    -0.06
     gonna
    -0.06
    spath
    -0.06
     UIB
    -0.06
    FormControl
    -0.06
     jobject
    -0.06
    Dog
    -0.06
     limit
    -0.06
    POSITIVE LOGITS
     "!
    0.06
    oner
    0.06
     clap
    0.06
    irector
    0.06
     وكانت
    0.06
     contentious
    0.06
     Frem
    0.06
     Olivier
    0.05
    …"
    0.05
     poměr
    0.05
    Act Density 0.094%

    No Known Activations