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

    Neuronpedia

    INDEX
    Explanations

    Organizations and initiatives

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     regex
    0.72
     malware
    0.61
     phishing
    0.59
     syntax
    0.59
     mutex
    0.59
     DHCP
    0.57
     idempot
    0.57
     vacuoles
    0.56
     Regex
    0.56
     VLAN
    0.55
    POSITIVE LOGITS
    The
    0.59
    Youth
    0.54
    Innovation
    0.52
    landmark
    0.52
    National
    0.52
    Journey
    0.51
    Center
    0.49
    Women
    0.49
    Alliance
    0.48
    Pathway
    0.48
    Act Density 0.251%

    No Known Activations