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

    Neuronpedia

    INDEX
    Explanations

    Arabic text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Torch
    -0.07
    xy
    -0.06
     asphalt
    -0.06
     proč
    -0.06
    yth
    -0.06
     Mundo
    -0.06
    _ped
    -0.06
     dah
    -0.06
     poultry
    -0.06
    	env
    -0.06
    POSITIVE LOGITS
    非
    0.07
     (;
    0.07
    حيح
    0.07
     اعمال
    0.06
    MEDIA
    0.06
    SizeMode
    0.06
     Executive
    0.06
    anim
    0.06
    layın
    0.06
     postData
    0.06
    Act Density 0.003%

    No Known Activations