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

    Neuronpedia

    INDEX
    Explanations

    technical terms and definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Corrections
    0.54
     Correctional
    0.47
     Computer
    0.46
     Comercio
    0.46
     Pint
    0.46
     Ashford
    0.46
     Arts
    0.46
     Computing
    0.46
     Flight
    0.46
     CIA
    0.46
    POSITIVE LOGITS
     rubble
    0.49
     sabotage
    0.47
     surgir
    0.46
     irresistible
    0.44
     alarming
    0.44
     arise
    0.44
    ުގައި
    0.44
     rupt
    0.43
     traumas
    0.43
    ମ
    0.43
    Act Density 0.001%

    No Known Activations