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

    Neuronpedia

    INDEX
    Explanations

    st

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Joseph
    -0.06
     ditch
    -0.06
     taky
    -0.06
     라
    -0.06
    ्रक
    -0.06
     baked
    -0.06
     Stre
    -0.06
     Joseph
    -0.06
    یمی
    -0.06
    ротив
    -0.06
    POSITIVE LOGITS
    ción
    0.07
    revision
    0.06
     επα
    0.06
    ','',
    0.06
    
    0.06
    (script
    0.06
    [v
    0.06
    ESA
    0.06
    lineEdit
    0.06
    BT
    0.06
    Act Density 0.162%

    No Known Activations