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

    Neuronpedia

    INDEX
    Explanations

    numbers and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    锒
    0.36
    ्रेन
    0.36
     paycheck
    0.34
     outbreak
    0.34
     mall
    0.34
     voter
    0.34
     electorate
    0.34
    یش
    0.33
     bomber
    0.33
     snacking
    0.33
    POSITIVE LOGITS
     giov
    0.40
     одном
    0.38
     Result
    0.35
     હતી
    0.35
    undefined
    0.35
    Initialization
    0.34
     Starts
    0.34
     没有
    0.34
     能
    0.34
    ximity
    0.34
    Act Density 0.007%

    No Known Activations