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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ॉम
    -0.08
    ())
↵
↵
    -0.07
    Education
    -0.07
    entifier
    -0.07
     हव
    -0.06
    identity
    -0.06
    ,
↵
↵
    -0.06
    İ
    -0.06
     stocking
    -0.06
    |↵
    -0.06
    POSITIVE LOGITS
    rina
    0.07
     Forums
    0.06
    (step
    0.06
     Crafting
    0.06
    になり
    0.06
     dripping
    0.06
    Drink
    0.06
    .groupBox
    0.06
     datePicker
    0.06
    .InnerException
    0.05
    Act Density 0.000%

    No Known Activations