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

    Neuronpedia

    INDEX
    Explanations

    code definitions and blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    benzene
    0.44
    --“
    0.42
     Slab
    0.37
    )="
    0.36
     benzene
    0.36
    thole
    0.36
    ikiem
    0.35
    ிலேயே
    0.35
     Kra
    0.35
    --"
    0.35
    POSITIVE LOGITS
     :
    1.16
    (:
    1.02
     `:
    0.85
     :'
    0.85
     (:
    0.84
     [:
    0.79
     :,
    0.77
     :{
    0.77
     :"
    0.73
     :#
    0.72
    Act Density 0.007%

    No Known Activations