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

    Neuronpedia

    INDEX
    Explanations

    request and explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ਵਿ
    0.51
     Solubility
    0.47
     ビタミン
    0.46
    vitro
    0.46
     Pupils
    0.46
     วิชา
    0.45
     bismuth
    0.45
     मैथमेटिक्स
    0.44
     flourished
    0.44
     vidhan
    0.44
    POSITIVE LOGITS
    Answer
    0.48
    arnings
    0.46
    Understand
    0.46
    вре
    0.46
    n
    0.45
    োর
    0.45
    о
    0.45
    iding
    0.44
    в
    0.44
    anking
    0.43
    Act Density 0.000%

    No Known Activations