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

    Neuronpedia

    INDEX
    Explanations

    get a, achieve key, clear understanding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    NM
    0.55
    UN
    0.53
    บอล
    0.50
    0.50
    UD
    0.49
    publicKey
    0.49
    Vậy
    0.46
    ronique
    0.46
    PM
    0.46
    膿
    0.44
    POSITIVE LOGITS
    は
    0.54
     punctuated
    0.51
     accented
    0.50
     unfilled
    0.49
    など
    0.49
     viewpoints
    0.46
    кло
    0.46
     instead
    0.46
     invece
    0.46
    किल
    0.46
    Act Density 0.000%

    No Known Activations