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

    Neuronpedia

    INDEX
    Explanations

    json content type

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    зир
    0.43
     murals
    0.40
    rootDir
    0.39
    ardom
    0.39
     cries
    0.39
     quinto
    0.39
     raided
    0.38
     tinham
    0.38
    linhas
    0.38
     couro
    0.38
    POSITIVE LOGITS
    json
    0.48
    octet
    0.39
     forced
    0.38
     Boltzmann
    0.38
    日
    0.37
    老
    0.36
     जाति
    0.36
    plicated
    0.36
    על
    0.35
    占
    0.35
    Act Density 0.000%

    No Known Activations