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

    Neuronpedia

    INDEX
    Explanations

    presence and impact of individuals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     suspect
    0.73
     extrapol
    0.65
     handling
    0.64
    ่ย
    0.63
    थन
    0.61
     manipulator
    0.60
     pomoć
    0.60
     gauging
    0.59
     upgrading
    0.59
     quasi
    0.59
    POSITIVE LOGITS
     presence
    1.14
    presence
    1.07
     legacy
    1.07
    Presence
    1.06
    存在
    1.04
     legacies
    0.99
     memory
    0.98
     Presence
    0.98
     existir
    0.97
    legacy
    0.97
    Act Density 0.042%

    No Known Activations