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

    Neuronpedia

    INDEX
    Explanations

    positive reviews or travel recommendations

    oai_token-act-pair · gemini-2.0-flash

    promotional/descriptive content

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.59
     елның
    -0.57
    adaptiveStyles
    -0.52
    RegressionTest
    -0.52
     تضيفلها
    -0.49
     onCancelled
    -0.48
    uens
    -0.46
    sequelize
    -0.44
     Obtén
    -0.43
    енча
    -0.43
    POSITIVE LOGITS
    bootstrapcdn
    0.69
    AddTagHelper
    0.65
     esternos
    0.59
     litté
    0.54
    MENAFN
    0.54
     smtplib
    0.51
    WriteTagHelper
    0.51
     onda
    0.51
     snippetHide
    0.50
     inwest
    0.50
    Act Density 0.630%

    No Known Activations