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

    Neuronpedia

    INDEX
    Explanations

    direction words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     otomatig
    -0.66
    зулта
    -0.64
    droje
    -0.63
     beſt
    -0.61
     AssemblyCulture
    -0.61
     ſtate
    -0.59
     ſtand
    -0.59
    ()}}
    -0.58
     ſhould
    -0.58
    WebServlet
    -0.58
    POSITIVE LOGITS
     along
    0.79
     Along
    0.71
    Along
    0.64
    along
    0.57
     ALONG
    0.54
    Rhestr
    0.53
    uxxxx
    0.49
    alu
    0.48
     Through
    0.44
    الدراسه
    0.44
    Act Density 0.000%

    No Known Activations