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

    Neuronpedia

    INDEX
    Explanations

    humans versus other animals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ็
    -0.07
    .activities
    -0.07
    話
    -0.07
     Мак
    -0.06
    عر
    -0.06
    oor
    -0.06
     ول
    -0.06
    �
    -0.06
    �
    -0.06
    []"
    -0.06
    POSITIVE LOGITS
    (range
    0.07
     Winds
    0.07
     conta
    0.06
     combo
    0.06
     送
    0.06
    STITUTE
    0.06
    Variables
    0.06
     geç
    0.06
     tweets
    0.06
     adulte
    0.06
    Act Density 0.009%

    No Known Activations