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

    Neuronpedia

    INDEX
    Explanations

    directory, Active Directory

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cybersecurity
    0.46
    Oo
    0.44
     drivetrain
    0.44
     Safari
    0.43
     melt
    0.42
     Congo
    0.42
     border
    0.41
     smartphones
    0.41
     spectacle
    0.41
     Covid
    0.41
    POSITIVE LOGITS
    nut
    0.52
    april
    0.49
    chi
    0.48
    ll
    0.47
    sulf
    0.46
    directory
    0.43
    fillStyle
    0.43
    phosphory
    0.43
    nl
    0.43
    nc
    0.42
    Act Density 0.007%

    No Known Activations