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

    Neuronpedia

    INDEX
    Explanations

    time after meal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dragging
    0.24
     badass
    0.24
     raging
    0.24
    nivel
    0.23
     duality
    0.22
     poquito
    0.22
     horrendous
    0.22
    destino
    0.22
    ؟!
    0.21
    nodo
    0.21
    POSITIVE LOGITS
    使
    0.23
     Laboratories
    0.21
    Research
    0.20
    &
    0.20
     Research
    0.20
     小
    0.20
     Technology
    0.20
    \
    0.19
    &\
    0.19
    CF
    0.19
    Act Density 0.007%

    No Known Activations