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

    Neuronpedia

    INDEX
    Explanations

    the word "these" and "those"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uries
    -0.08
    semblies
    -0.07
    urrencies
    -0.07
    untas
    -0.07
    agens
    -0.07
    ksam
    -0.07
    kich
    -0.06
    dration
    -0.06
     (*((
    -0.06
    аÑĤкÑĥ
    -0.06
    POSITIVE LOGITS
     surroundings
    0.09
     coordinates
    0.09
     stairs
    0.08
     guidelines
    0.08
     circumstances
    0.08
     credentials
    0.08
     instructions
    0.08
     few
    0.08
     proceedings
    0.08
     words
    0.08
    Act Density 0.080%

    No Known Activations