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

    Neuronpedia

    INDEX
    Explanations

    say '*'

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     consenso
    0.44
     hydrology
    0.44
     🤔
    0.43
    लरशिप
    0.43
     succinctly
    0.43
     infestations
    0.42
     exorbit
    0.42
     strawberries
    0.42
     cosplay
    0.42
    abhavena
    0.42
    POSITIVE LOGITS
    *
    0.96
     *
    0.81
    \*
    0.60
    *.
    0.56
    --
    0.50
    *(
    0.50
    *}
    0.49
    *\
    0.49
    *"
    0.49
    0.49
    Act Density 1.430%

    No Known Activations