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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     surla
    -0.85
    windowFixed
    -0.72
    ⓧ
    -0.59
     Efq
    -0.58
     continúas
    -0.56
    __((
    -0.56
     Mutant
    -0.55
     Cataloging
    -0.55
    <bos>
    -0.53
     <<<<<<<<<<<<<<
    -0.53
    POSITIVE LOGITS
    0
    0.82
    5
    0.67
     Exacts
    0.49
    FileDescriptor
    0.47
    relser
    0.45
     CreateTagHelper
    0.40
    ignac
    0.40
    cloudfront
    0.37
    addContainerGap
    0.37
    getSeconds
    0.36
    Act Density 0.030%

    No Known Activations