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

    Neuronpedia

    INDEX
    Explanations

    row

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     translation
    -0.08
     псих
    -0.07
     freder
    -0.07
    회
    -0.07
     jedno
    -0.06
     MIT
    -0.06
     infrared
    -0.06
    Typ
    -0.06
     spend
    -0.06
     दस
    -0.06
    POSITIVE LOGITS
    caption
    0.07
    <article
    0.07
    egasus
    0.06
    	UObject
    0.06
     Scalars
    0.06
    .camel
    0.06
    .rmi
    0.06
     bé
    0.06
    metro
    0.06
     Breast
    0.05
    Act Density 0.009%

    No Known Activations