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

    Neuronpedia

    INDEX
    Explanations

    the word 'appointment'

    oai_token-act-pair · gemini-2.0-flash

    appointment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    __":
    -0.88
    SBATCH
    -0.85
    MLLoader
    -0.84
    somebody
    -0.84
    __":
    -0.82
    __':
    -0.82
    pperware
    -0.79
     <=",
    -0.77
     дописавши
    -0.75
    __':
    -0.75
    POSITIVE LOGITS
     iſt
    0.83
     ſy
    0.81
     quæ
    0.79
     auffi
    0.79
     ſind
    0.79
     themſelves
    0.77
     ſtate
    0.77
     whoſe
    0.77
     ſol
    0.76
     diſt
    0.75
    Act Density 0.532%

    No Known Activations