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

    Neuronpedia

    INDEX
    Explanations

    interrogation or questioning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lizenz
    -0.82
    ardia
    -0.80
    ванные
    -0.79
    一颗
    -0.78
     encapsulation
    -0.75
     Huntingdon
    -0.75
    aviar
    -0.75
     στιγ
    -0.75
     сахара
    -0.74
     berço
    -0.73
    POSITIVE LOGITS
     interrogation
    2.72
     questioning
    2.50
     interrog
    2.38
     interrogated
    2.00
     grilling
    1.99
     questioned
    1.88
     grilled
    1.70
     interview
    1.60
     grill
    1.59
     interro
    1.47
    Act Density 0.030%

    No Known Activations