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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _empty
    -0.07
     цель
    -0.07
     textiles
    -0.07
    ẹ
    -0.07
     textile
    -0.07
     vlády
    -0.06
     current
    -0.06
     pod
    -0.06
    卷
    -0.06
    	value
    -0.06
    POSITIVE LOGITS
     определен
    0.07
     Narc
    0.07
     ikt
    0.06
     Blue
    0.06
     unimagin
    0.06
     Ter
    0.06
    .He
    0.06
    (Is
    0.06
    า�
    0.06
     Asphalt
    0.06
    Act Density 0.006%

    No Known Activations