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

    Neuronpedia

    INDEX
    Explanations

    Histories, rhythm, odd locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     MSG
    0.50
     Bluetooth
    0.49
     Interpreter
    0.46
     ni
    0.46
     Instagram
    0.46
     bartender
    0.45
     hotel
    0.44
     ads
    0.44
     unwelcome
    0.44
     walkers
    0.43
    POSITIVE LOGITS
    Patient
    0.58
    Chair
    0.53
    Curr
    0.53
    Rest
    0.52
    Econom
    0.51
    Czech
    0.50
     preparazione
    0.50
    Arch
    0.50
    Cur
    0.50
    econom
    0.50
    Act Density 0.004%

    No Known Activations