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

    Neuronpedia

    INDEX
    Explanations

    which one / entity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     drauf
    0.90
     Yuri
    0.79
     auf
    0.79
     عليها
    0.78
     tightening
    0.78
     iets
    0.77
     tightness
    0.77
     tagging
    0.77
    novae
    0.76
     markers
    0.76
    POSITIVE LOGITS
     이러한
    0.84
    мно
    0.83
    Correspondence
    0.83
    片
    0.82
    κα
    0.81
    全国
    0.80
    ած
    0.80
     Signed
    0.79
     חש
    0.79
     оча
    0.78
    Act Density 0.000%

    No Known Activations