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

    Neuronpedia

    INDEX
    Explanations

    Technical/Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     serr
    -0.29
    å¦Ļ
    -0.28
    寡
    -0.27
    .records
    -0.27
     juven
    -0.26
    olics
    -0.26
     Sachs
    -0.25
     Pulitzer
    -0.25
    odelist
    -0.25
    æĬĦ
    -0.25
    POSITIVE LOGITS
    scopes
    0.29
    -na
    0.27
     units
    0.26
    Cow
    0.25
     attention
    0.24
     kin
    0.24
    è¯ķ
    0.24
    vision
    0.24
    _na
    0.23
    -ca
    0.23
    Act Density 0.008%

    No Known Activations