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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Communication
    -0.08
     communication
    -0.08
    ---↵
    -0.08
    communication
    -0.08
     avantaj
    -0.07
     advantageous
    -0.07
    ایش
    -0.07
    _extension
    -0.07
    Contributor
    -0.07
    virt
    -0.07
    POSITIVE LOGITS
     Folgen
    0.08
     Schulen
    0.08
    orthern
    0.08
     فبراير
    0.08
     فعل
    0.08
     பழ
    0.08
     اللبنانية
    0.08
     Hamburg
    0.07
     seguida
    0.07
     Tom
    0.07
    Act Density 0.003%

    No Known Activations