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

    Neuronpedia

    INDEX
    Explanations

    Scientific research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	base
    -0.07
     Country
    -0.07
    postcode
    -0.07
    hk
    -0.07
    exclude
    -0.06
     colomb
    -0.06
     Pep
    -0.06
    706
    -0.06
    Defaults
    -0.06
    _third
    -0.06
    POSITIVE LOGITS
    :not
    0.07
    togroup
    0.06
     �
    0.06
     thí
    0.06
     IDictionary
    0.06
    γει
    0.06
    ordin
    0.06
    illet
    0.06
    ันธ
    0.06
     loneliness
    0.06
    Act Density 0.148%

    No Known Activations