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

    Neuronpedia

    INDEX
    Explanations

    sliding doors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <0x0D>
    0.71
                        
    0.70
    ר
    0.64
    ر
    0.63
         
    0.61
    К
    0.60
          
    0.60
    0.59
    Ча
    0.58
               
    0.57
    POSITIVE LOGITS
    ros
    0.60
    सर्गिक
    0.54
    deg
    0.54
    ming
    0.53
    izes
    0.53
    orsement
    0.52
    сах
    0.52
    ices
    0.51
    door
    0.51
    nesses
    0.51
    Act Density 0.000%

    No Known Activations