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

    Neuronpedia

    INDEX
    Explanations

    renovations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Manager
    -0.07
    Career
    -0.06
    dict
    -0.06
    -server
    -0.06
     hatch
    -0.06
     einer
    -0.06
    824
    -0.06
    iotics
    -0.06
     Bachelor
    -0.06
    lem
    -0.06
    POSITIVE LOGITS
    -cross
    0.07
    рол
    0.07
     SH
    0.06
     xlabel
    0.06
     akci
    0.06
     εμφ
    0.06
     uuid
    0.06
    เปอร
    0.06
     doğ
    0.06
    _ACC
    0.06
    Act Density 0.024%

    No Known Activations