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

    Neuronpedia

    INDEX
    Explanations

    Acc word endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     transformations
    0.74
     patties
    0.71
     vomit
    0.69
     inher
    0.67
     socio
    0.67
     cons
    0.67
     around
    0.67
     vidare
    0.64
     further
    0.63
     importantly
    0.63
    POSITIVE LOGITS
    modation
    1.43
    adem
    1.21
    urate
    1.21
    ronym
    1.14
    ADEM
    1.05
    ropolis
    1.04
    ademia
    1.04
    idental
    1.01
    cepat
    1.00
    entu
    0.99
    Act Density 0.035%

    No Known Activations