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

    Neuronpedia

    INDEX
    Explanations

    impressed, shocked

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     disambiguazione
    -0.58
    IUrlHelper
    -0.53
    oa̍t
    -0.49
    TextInputLayout
    -0.47
    ïque
    -0.46
    Стро
    -0.45
    Reuters
    -0.43
    tonsoft
    -0.42
    ikit
    -0.42
     Schult
    -0.42
    POSITIVE LOGITS
     otomatig
    0.75
    clable
    0.67
     protoimpl
    0.63
    Šaltiniai
    0.60
     ComVisible
    0.59
     Fen
    0.57
    RegressionTest
    0.56
    agne
    0.56
     <<<<<<<<<<<<<<
    0.55
    uremberg
    0.53
    Act Density 0.036%

    No Known Activations