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

    Neuronpedia

    INDEX
    Explanations

    quarantine and isolation procedures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cambiamento
    0.44
    ンダー
    0.43
     мировой
    0.42
    Ignoring
    0.42
     comportamiento
    0.41
     indestructible
    0.41
     ambivalent
    0.41
     ટકા
    0.41
     hardening
    0.40
    Steven
    0.40
    POSITIVE LOGITS
     quarantine
    0.91
     quarantined
    0.91
    隔离
    0.89
    隔離
    0.86
     quarant
    0.82
     Quarantine
    0.82
    isolation
    0.80
     isolation
    0.79
    isolate
    0.78
     isolate
    0.78
    Act Density 0.016%

    No Known Activations