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

    Neuronpedia

    INDEX
    Explanations

    one two or HTTP Error

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    idavit
    0.33
    橘
    0.33
    ською
    0.32
    lywood
    0.31
    Доб
    0.31
    Robertson
    0.30
     visualiser
    0.30
    朓
    0.30
     وم
    0.30
    berta
    0.30
    POSITIVE LOGITS
     혹
    0.34
     -----
    0.31
     Costs
    0.31
     ----
    0.31
    <0xC2>
    0.30
     никаких
    0.30
    IfExists
    0.30
     "-----
    0.29
     കൂടുതൽ
    0.29
     ControllerBase
    0.29
    Act Density 0.012%

    No Known Activations