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

    Neuronpedia

    INDEX
    Explanations

    open weights

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Joe
    0.40
     Joe
    0.39
    Poke
    0.39
     охорони
    0.39
     Integrative
    0.39
    pony
    0.39
     joe
    0.38
     integrative
    0.38
    Joseph
    0.37
     Rass
    0.37
    POSITIVE LOGITS
     Em
    0.39
     Pad
    0.37
     pad
    0.35
     ава
    0.35
    west
    0.34
    Pad
    0.34
    peda
    0.33
     Pedal
    0.33
    pad
    0.32
    acet
    0.32
    Act Density 0.015%

    No Known Activations