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

    Neuronpedia

    INDEX
    Explanations

    on [preposition] state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Activation
    0.40
    Banner
    0.40
    Conditions
    0.39
    banner
    0.38
     invoke
    0.38
    REQUEST
    0.37
     invoking
    0.36
     Verfügung
    0.36
     요구
    0.36
    ingresso
    0.36
    POSITIVE LOGITS
     vacation
    0.84
     fumes
    0.63
     tenter
    0.63
     probation
    0.60
     Vacation
    0.59
     sabbatical
    0.58
     holiday
    0.57
     vacations
    0.56
     lookout
    0.55
     autopilot
    0.55
    Act Density 0.011%

    No Known Activations