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

    Neuronpedia

    INDEX
    Explanations

    speed and focus

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Vallarta
    -0.44
    HasForeignKey
    -0.43
     exercised
    -0.43
    Бахар
    -0.42
    soever
    -0.41
     تجاه
    -0.40
    <bos>
    -0.40
     profiled
    -0.40
     nature
    -0.38
    amate
    -0.38
    POSITIVE LOGITS
     nahilalakip
    0.84
    tagHelperRunner
    0.72
     snippetHide
    0.69
    ंदीखरीदारी
    0.69
     Prediction
    0.68
     CreateTagHelper
    0.68
     دیکھیے
    0.66
     Suffering
    0.65
     Reproduce
    0.64
    IntoConstraints
    0.63
    Act Density 0.011%

    No Known Activations