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

    Neuronpedia

    INDEX
    Explanations

    filtration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nok
    -0.07
     القوات
    -0.06
    <pcl
    -0.06
    .childNodes
    -0.06
     Feast
    -0.06
    _CAST
    -0.06
     plaint
    -0.06
     xpos
    -0.06
    (Util
    -0.06
     stalk
    -0.06
    POSITIVE LOGITS
     wegen
    0.07
    侹
    0.07
    Ⰽ
    0.07
     surgery
    0.07
    👳
    0.07
    acute
    0.07
    pan
    0.07
    öff
    0.07
     Under
    0.07
    porte
    0.06
    Act Density 0.004%

    No Known Activations