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

    Neuronpedia

    INDEX
    Explanations

    direction/control

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    352
    -0.06
     tote
    -0.06
    qus
    -0.06
     по
    -0.06
    _cf
    -0.06
     Belediye
    -0.06
     ΣΤ
    -0.06
    fft
    -0.06
     रह
    -0.06
     rentals
    -0.06
    POSITIVE LOGITS
    approved
    0.06
    クション
    0.06
    	system
    0.06
     Elastic
    0.06
    이는
    0.06
    //#
    0.06
    ば
    0.06
    woff
    0.06
    ัมพ
    0.06
    зи
    0.06
    Act Density 0.036%

    No Known Activations