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

    Neuronpedia

    INDEX
    Explanations

    going to be

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    АС
    0.65
     لوبو
    0.65
     پیغم
    0.64
    HAS
    0.62
    comers
    0.62
    MGMT
    0.61
    ASCADE
    0.61
    ﻥ
    0.60
    AIN
    0.59
    Cancelar
    0.59
    POSITIVE LOGITS
            
    0.63
                        
    0.57
    ar
    0.55
    网
    0.53
          
    0.51
    的所有
    0.50
                
    0.50
    无比
    0.50
        
    0.49
    <0x0D>
    0.49
    Act Density 0.029%

    No Known Activations