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

    Neuronpedia

    INDEX
    Explanations

    News article/documentary text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     distraction
    -0.07
     сразу
    -0.07
    acro
    -0.07
    Dev
    -0.07
    别人
    -0.06
    (Border
    -0.06
    ToJson
    -0.06
     школ
    -0.06
    אד
    -0.06
     barely
    -0.06
    POSITIVE LOGITS
     starttime
    0.08
     smallest
    0.07
    KeyName
    0.07
    ti
    0.07
     whipped
    0.07
    alty
    0.06
    �
    0.06
    营运
    0.06
     day
    0.06
    ling
    0.06
    Act Density 0.065%

    No Known Activations