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

    Neuronpedia

    INDEX
    Explanations

    any health concerns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Cuánt
    0.72
    த்தம்
    0.62
    Available
    0.60
    تالي
    0.59
    InnoDB
    0.58
    Socket
    0.57
     Socket
    0.55
    available
    0.55
    Weapon
    0.55
     Available
    0.54
    POSITIVE LOGITS
     and
    0.61
     лично
    0.59
     personally
    0.58
     indeed
    0.58
     namelijk
    0.54
    velles
    0.54
     microsc
    0.53
     intentions
    0.53
     personal
    0.53
    和
    0.52
    Act Density 0.016%

    No Known Activations