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

    Neuronpedia

    INDEX
    Explanations

    list items and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ditth
    0.54
    textepsilon
    0.51
    specifiedByURL
    0.51
     côt
    0.50
     splike
    0.50
     creato
    0.49
     thisComponent
    0.48
     linkCell
    0.48
     parete
    0.48
     mobili
    0.48
    POSITIVE LOGITS
    With
    0.50
    Un
    0.49
    :
    0.47
    Using
    0.46
    Боль
    0.46
    วัน
    0.46
    Ver
    0.45
    s
    0.44
    ด้วย
    0.44
    Exclusive
    0.44
    Act Density 0.000%

    No Known Activations