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

    Neuronpedia

    INDEX
    Explanations

    validation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (user
    -0.08
    :user
    -0.07
    	stream
    -0.07
    .timestamp
    -0.07
    Slow
    -0.07
     amplitude
    -0.06
    :%
    -0.06
     eos
    -0.06
    	super
    -0.06
    +"'
    -0.06
    POSITIVE LOGITS
     ModelRenderer
    0.07
    -либо
    0.06
     المللی
    0.06
     CBS
    0.06
    ιδ
    0.06
    rid
    0.06
     plagiarism
    0.06
     externally
    0.06
    serrat
    0.06
    ๆ
    0.06
    Act Density 0.005%

    No Known Activations