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

    Neuronpedia

    INDEX
    Explanations

    grasped

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lifier
    -0.60
    zei
    -0.59
     parsed
    -0.59
    nern
    -0.58
    ropolitan
    -0.55
    anyi
    -0.55
    cheng
    -0.54
    EndContext
    -0.54
     Leto
    -0.54
    ן
    -0.54
    POSITIVE LOGITS
    +#+#
    0.84
    s
    0.81
    RegressionTest
    0.73
     AssemblyCompany
    0.69
     Roskov
    0.63
     nonUne
    0.60
    NewUrlParser
    0.60
     OFDb
    0.59
     تانيه
    0.57
     TextInputType
    0.55
    Act Density 1.540%

    No Known Activations