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

    Neuronpedia

    INDEX
    Explanations

    joining

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	ResultSet
    -0.08
    豉
    -0.08
     recurs
    -0.08
    _Admin
    -0.07
     ambulance
    -0.07
     dramas
    -0.07
     Dun
    -0.07
    _SECURITY
    -0.07
     fruity
    -0.07
    -validate
    -0.07
    POSITIVE LOGITS
    早
    0.08
     себе
    0.07
    模式
    0.06
    赎
    0.06
    角落
    0.06
    
    0.06
     soar
    0.06
    暮
    0.06
    ﮍ
    0.06
     ок
    0.06
    Act Density 0.052%

    No Known Activations