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

    Neuronpedia

    INDEX
    Explanations

    best choice or right choice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    0.46
    <0x0D>
    0.45
        
    0.44
                
    0.44
    0.43
    }
    0.43
                    
    0.42
     }
    0.41
    }}$
    0.40
    },
    0.40
    POSITIVE LOGITS
     rangkaian
    0.45
    لل
    0.41
     whitelist
    0.40
     racionais
    0.40
     apariencia
    0.39
    ທີ່ຈະ
    0.39
     estética
    0.38
     comté
    0.38
     colocadas
    0.38
     imit
    0.38
    Act Density 0.016%

    No Known Activations