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

    Neuronpedia

    INDEX
    Explanations

    follow

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hobby
    -0.09
    scribe
    -0.09
     pockets
    -0.09
     timestamp
    -0.08
     crime
    -0.08
     groove
    -0.07
     cricket
    -0.07
     roster
    -0.07
     arguing
    -0.07
     grooves
    -0.07
    POSITIVE LOGITS
     redirects
    0.13
    _redirect
    0.12
    .Redirect
    0.11
    _follow
    0.11
    .follow
    0.10
    Follow
    0.10
     Follow
    0.10
    -follow
    0.10
    .redirect
    0.10
     Redirect
    0.10
    Act Density 0.004%

    No Known Activations