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

    Neuronpedia

    INDEX
    Explanations

    data entry clerks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sning
    1.09
    OWL
    1.07
     downlink
    1.05
     Tf
    1.01
    ASE
    0.96
     Sabre
    0.94
     $=$
    0.94
     warmest
    0.93
    Ī
    0.91
    ﺎ
    0.91
    POSITIVE LOGITS
     organisms
    1.08
     जीवों
    0.99
     espos
    0.96
     creatures
    0.92
     critters
    0.91
    organisms
    0.90
     além
    0.90
     spies
    0.86
     totalSupply
    0.86
     organism
    0.86
    Act Density 0.000%

    No Known Activations