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

    Neuronpedia

    INDEX
    Explanations

    the of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     služby
    -0.08
     rq
    -0.07
     judiciary
    -0.07
    "When
    -0.06
    "In
    -0.06
    "We
    -0.06
     Mil
    -0.06
    Bước
    -0.06
    'We
    -0.06
    “In
    -0.06
    POSITIVE LOGITS
    aye
    0.07
    اجر
    0.07
     Hawaiian
    0.06
    idia
    0.06
    ния
    0.06
     sword
    0.06
     Events
    0.06
    	parent
    0.06
    iane
    0.06
    忠
    0.06
    Act Density 0.046%

    No Known Activations