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

    Neuronpedia

    INDEX
    Explanations

    hostage situations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reproduc
    -0.08
     responsable
    -0.08
     samf
    -0.08
     ecosystem
    -0.08
     ecosystems
    -0.08
     kingdoms
    -0.07
     অপর
    -0.07
     diet
    -0.07
     לה
    -0.07
     kres
    -0.07
    POSITIVE LOGITS
     psychiatric
    0.10
    atika
    0.10
     hostage
    0.09
     trapped
    0.09
    .dialog
    0.09
    Locked
    0.09
    Interior
    0.09
    Tat
    0.09
     terrorists
    0.09
    (dialog
    0.08
    Act Density 0.022%

    No Known Activations