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

    Neuronpedia

    INDEX
    Explanations

    start row/column definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     obtenidos
    0.90
     estadounidenses
    0.87
     vitth
    0.85
    ্জন
    0.84
    ਤੀ
    0.83
    यॉर्क
    0.82
    ayutt
    0.82
     escuchar
    0.82
    avasena
    0.82
     comenzar
    0.81
    POSITIVE LOGITS
    INTER
    0.79
                        
    0.63
        
    0.63
    PART
    0.63
    obacterium
    0.61
    actionBar
    0.61
    UTR
    0.60
    |
    0.60
    en
    0.59
     Jacks
    0.58
    Act Density 0.007%

    No Known Activations