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

    Neuronpedia

    INDEX
    Explanations

    weapons/combat

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     졸
    -0.06
     спів
    -0.06
    embre
    -0.06
    лад
    -0.06
    Uvs
    -0.06
     Wolverine
    -0.06
    ани
    -0.06
    от
    -0.06
    /front
    -0.06
     요
    -0.06
    POSITIVE LOGITS
    Contacts
    0.08
    >',↵
    0.07
    染
    0.07
    制
    0.07
    Desk
    0.07
    kaar
    0.06
     offset
    0.06
     foreseeable
    0.06
     bilateral
    0.06
     anthropology
    0.06
    Act Density 0.012%

    No Known Activations