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

    Neuronpedia

    INDEX
    Explanations

    require

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bash
    -0.08
     mods
    -0.08
     jump
    -0.08
     hints
    -0.07
     host
    -0.07
    host
    -0.07
    band
    -0.07
    hosts
    -0.07
    boxing
    -0.07
     lamb
    -0.07
    POSITIVE LOGITS
     requires
    0.16
     require
    0.13
     requiring
    0.12
     Requires
    0.11
     required
    0.11
     Require
    0.10
    requires
    0.09
    Require
    0.09
    require
    0.09
    .require
    0.09
    Act Density 0.035%

    No Known Activations