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

    Neuronpedia

    INDEX
    Explanations

    violate guidelines or rules

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     forbindelse
    0.83
    னை
    0.82
     защи
    0.79
    во
    0.77
    汅
    0.76
     μαζί
    0.75
    ৩৮
    0.75
     শ্রমিক
    0.75
    뛸
    0.75
    0.75
    POSITIVE LOGITS
    h
    1.12
     standards
    1.01
     normas
    1.00
     norms
    0.98
     norme
    0.96
     требований
    0.91
     rules
    0.91
     вимо
    0.90
     stringent
    0.90
     requirements
    0.89
    Act Density 0.435%

    No Known Activations