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

    Neuronpedia

    INDEX
    Explanations

    hostage and ransom

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ખ્ય
    0.66
    ğın
    0.59
     ενεργ
    0.59
    كثر
    0.57
    w
    0.56
    ال
    0.55
    ز
    0.55
    al
    0.55
     المثلثيه
    0.54
    Daisy
    0.54
    POSITIVE LOGITS
     hostage
    1.06
     hostages
    1.06
     kidnapped
    1.01
     kidnapping
    0.98
     kidnap
    0.91
     kidn
    0.87
     Ransom
    0.80
     captives
    0.80
     ransom
    0.79
     captivity
    0.71
    Act Density 0.046%

    No Known Activations