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

    Neuronpedia

    INDEX
    Explanations

    xml namespaces and types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    том
    0.65
    s
    0.54
    сона
    0.50
    ண்முக
    0.50
    ǒu
    0.50
     Wehr
    0.50
    sockfd
    0.50
    ையைக்
    0.49
    socket
    0.49
    sning
    0.49
    POSITIVE LOGITS
    _
    0.66
     bends
    0.64
     tutors
    0.64
     arrears
    0.60
     integrals
    0.59
    의
    0.58
     molds
    0.57
     fright
    0.55
     increí
    0.55
     addictions
    0.55
    Act Density 0.001%

    No Known Activations