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

    Neuronpedia

    INDEX
    Explanations

    endorse, support, advocate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     дося
    0.42
     interactivity
    0.39
     handled
    0.39
    Manip
    0.38
     Handling
    0.38
    实在
    0.38
    Lever
    0.37
    ⊷
    0.37
     osią
    0.37
     পারা
    0.37
    POSITIVE LOGITS
     endorsing
    1.72
     ủng
    1.65
     endorse
    1.62
     endors
    1.59
    支持
    1.52
     endorsement
    1.52
     advocating
    1.50
     apoyar
    1.48
     সমর্থন
    1.47
     apoyo
    1.44
    Act Density 0.039%

    No Known Activations