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

    Neuronpedia

    INDEX
    Explanations

    partial

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mish
    -0.08
     Mormon
    -0.08
    andin
    -0.07
     medic
    -0.07
    Minor
    -0.07
     choked
    -0.07
    獸
    -0.07
    _met
    -0.07
     жив
    -0.07
     discouraged
    -0.07
    POSITIVE LOGITS
     Barth
    0.07
     Locke
    0.07
    (lbl
    0.06
    Item
    0.06
    시장
    0.06
    	expect
    0.06
     ca
    0.06
    十四条
    0.06
     Free
    0.06
    dıklarını
    0.06
    Act Density 0.009%

    No Known Activations