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

    Neuronpedia

    INDEX
    Explanations

    console

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pog
    -0.07
    _staff
    -0.06
     indicted
    -0.06
    ़ी
    -0.06
    ньої
    -0.06
    ataka
    -0.06
    .property
    -0.06
    問題
    -0.06
    А
    -0.06
    ะแ
    -0.06
    POSITIVE LOGITS
    /list
    0.09
     skill
    0.07
     overdue
    0.07
    ends
    0.07
    	this
    0.06
    INUE
    0.06
    �
    0.06
    late
    0.06
    іду
    0.06
     correspond
    0.06
    Act Density 0.013%

    No Known Activations