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

    Neuronpedia

    INDEX
    Explanations

    skunks, html, protocols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    one
    0.55
    Beware
    0.52
    random
    0.50
    Additional
    0.50
    additional
    0.50
    Ideal
    0.49
    future
    0.49
    Sleep
    0.48
    ONE
    0.48
    P
    0.48
    POSITIVE LOGITS
     როგორ
    0.47
     Protocols
    0.46
     Bobby
    0.46
     Qc
    0.45
     Resorts
    0.45
     如何
    0.45
     multiSelectList
    0.45
     Protocol
    0.44
     Polynomial
    0.43
     Aaj
    0.43
    Act Density 0.055%

    No Known Activations