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

    Neuronpedia

    INDEX
    Explanations

    prefix

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reun
    -0.08
     entender
    -0.07
     lý
    -0.07
     نيوز
    -0.07
    _MONITOR
    -0.06
     nutzen
    -0.06
    לו
    -0.06
    掊
    -0.06
    ậm
    -0.06
     sein
    -0.06
    POSITIVE LOGITS
     billboard
    0.07
    igidbody
    0.07
     Nob
    0.07
     preservation
    0.07
    (ax
    0.06
    azines
    0.06
    各種
    0.06
    ")]
↵
    0.06
     отдел
    0.06
     Briggs
    0.06
    Act Density 0.005%

    No Known Activations