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

    Neuronpedia

    INDEX
    Explanations

    departmental or organizational names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Terminator
    0.29
     Chipotle
    0.29
     Cortana
    0.28
     Rx
    0.27
     Wolverine
    0.27
     Snyder
    0.27
     Prius
    0.27
     Therm
    0.26
     Theta
    0.26
     Neuron
    0.25
    POSITIVE LOGITS
     departamento
    0.29
     وزارت
    0.29
     sciences
    0.29
     национа
    0.28
     وزارة
    0.28
    Ș
    0.27
     nacional
    0.26
    貿
    0.26
    ин
    0.26
     ciencias
    0.26
    Act Density 0.062%

    No Known Activations