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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mist
    -0.07
     hans
    -0.07
     Dollars
    -0.07
    .textContent
    -0.07
     Miles
    -0.06
    נד
    -0.06
     Barrett
    -0.06
    ceil
    -0.06
     understanding
    -0.06
     CCP
    -0.06
    POSITIVE LOGITS
     행
    0.07
    �
    0.07
    composite
    0.07
    اظ
    0.07
    .setup
    0.07
    �
    0.07
    activities
    0.06
    XXXXXXXX
    0.06
     helicopt
    0.06
    财运
    0.06
    Act Density 0.000%

    No Known Activations