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

    Neuronpedia

    INDEX
    Explanations

    urls followed by slashes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -(
    0.59
    -
    0.57
    -[
    0.48
    -"+
    0.47
    -<
    0.45
    -*
    0.45
    -'+
    0.45
    -{
    0.45
     ноября
    0.44
    -|
    0.44
    POSITIVE LOGITS
     आलेल्या
    0.38
    長的
    0.37
    Allocation
    0.36
     استقبال
    0.35
    úan
    0.35
    उंट
    0.34
    फॉर्मेशन
    0.34
    华人
    0.34
     ब्लॉ
    0.34
    Entering
    0.34
    Act Density 0.002%

    No Known Activations