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

    Neuronpedia

    INDEX
    Explanations

    precedes price

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    etes
    0.39
     nerv
    0.38
    ogni
    0.38
     admi
    0.37
    jiv
    0.37
     totally
    0.37
     suda
    0.36
    ību
    0.36
    तरा
    0.36
     unreasonable
    0.36
    POSITIVE LOGITS
     Preview
    0.78
    Preview
    0.76
     preview
    0.72
    预览
    0.72
    preview
    0.70
     previews
    0.63
    Previews
    0.59
     orientation
    0.54
     تصویر
    0.54
    orientation
    0.54
    Act Density 0.000%

    No Known Activations