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

    Neuronpedia

    INDEX
    Explanations

    something breaking

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     св
    -0.07
     graphite
    -0.06
     yüzden
    -0.06
    |"
    -0.06
     hashtags
    -0.06
    self
    -0.06
    ?}",
    -0.06
    )?$
    -0.06
     Prom
    -0.06
    bv
    -0.06
    POSITIVE LOGITS
    lendi
    0.06
    เภท
    0.06
     Executive
    0.06
    inctions
    0.06
     pressures
    0.06
    PickerController
    0.06
     analyst
    0.06
     terminating
    0.06
    sembly
    0.06
    ......
    0.06
    Act Density 0.057%

    No Known Activations