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

    Neuronpedia

    INDEX
    Explanations

    underscore

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     moo
    -0.08
     RENDER
    -0.08
    жить
    -0.08
     Beau
    -0.07
     MQTT
    -0.07
    _genes
    -0.07
    �
    -0.07
     fren
    -0.07
    触
    -0.07
     havoc
    -0.07
    POSITIVE LOGITS
     algorithms
    0.08
     ضمن
    0.07
    extension
    0.07
     segregation
    0.07
     lowering
    0.07
     ArgumentException
    0.07
    (ad
    0.07
     endorsing
    0.07
     incorporation
    0.07
     analogous
    0.06
    Act Density 0.018%

    No Known Activations