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

    Neuronpedia

    INDEX
    Explanations

    saving code and 3d models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Mental
    0.39
     despised
    0.37
    Mental
    0.35
    ്ര
    0.35
     деся
    0.34
     अनुरोध
    0.34
     kahi
    0.34
     למ
    0.33
     sentito
    0.33
     Aff
    0.33
    POSITIVE LOGITS
    DialogInterface
    0.35
     fearless
    0.35
     لگے
    0.35
     direc
    0.34
    nico
    0.33
    émique
    0.33
    |.|
    0.32
    डान
    0.32
    get
    0.32
     विवेक
    0.32
    Act Density 0.002%

    No Known Activations