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

    Neuronpedia

    INDEX
    Explanations

    Laguna Blanca, gel, clone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ўцаў
    0.74
    ки
    0.66
    to
    0.64
    satisf
    0.61
    원을
    0.61
    itteln
    0.61
    τικός
    0.61
    км
    0.57
    cF
    0.56
    eOut
    0.56
    POSITIVE LOGITS
    ר
    0.69
    olla
    0.69
    ların
    0.68
     a
    0.68
    ن
    0.67
     d
    0.64
    ه
    0.64
    Í
    0.63
    </h2>
    0.62
    ##
    0.59
    Act Density 0.001%

    No Known Activations