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

    Neuronpedia

    INDEX
    Explanations

    time duration in minutes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Mays
    0.50
    vcxproj
    0.50
     Lis
    0.48
    anatom
    0.48
     Mayfield
    0.47
    ছনে
    0.47
     riverside
    0.47
    gebied
    0.47
     Dover
    0.46
    mell
    0.46
    POSITIVE LOGITS
     νέα
    0.52
     материал
    0.52
     वाढ
    0.50
     گے۔
    0.49
     deceive
    0.49
     XGB
    0.48
     процен
    0.48
     reinstate
    0.48
     cihaz
    0.47
     materiais
    0.47
    Act Density 0.000%

    No Known Activations