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

    Neuronpedia

    INDEX
    Explanations

    GitHub usernames and project names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     COVID
    0.45
     impact
    0.39
    COVID
    0.39
     cybersecurity
    0.39
     weatherproof
    0.38
     habitat
    0.38
     FCC
    0.37
    mipmap
    0.37
     global
    0.37
     Sections
    0.36
    POSITIVE LOGITS
     chris
    0.61
    guy
    0.59
    chris
    0.58
     dave
    0.57
    hombre
    0.55
     Chris
    0.54
     Mike
    0.54
    Mike
    0.54
    Dave
    0.54
    ib
    0.54
    Act Density 0.005%

    No Known Activations