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

    Neuronpedia

    INDEX
    Explanations

    $

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _variables
    -0.07
    amide
    -0.07
     fungus
    -0.07
    failed
    -0.07
     guidelines
    -0.06
    mel
    -0.06
    "name
    -0.06
    Components
    -0.06
     phối
    -0.06
     inspection
    -0.06
    POSITIVE LOGITS
     отли
    0.06
    -Л
    0.06
    」的
    0.06
    olem
    0.06
    930
    0.06
     anglais
    0.06
     refl
    0.06
    ですが
    0.06
     accused
    0.06
    děpodob
    0.06
    Act Density 0.018%

    No Known Activations