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

    Neuronpedia

    INDEX
    Explanations

    Questions & Calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Maul
    -0.07
     Kul
    -0.07
     Gard
    -0.07
     Prism
    -0.07
    alloc
    -0.07
     �
    -0.06
     Méd
    -0.06
    前所
    -0.06
    /utils
    -0.06
    在这种
    -0.06
    POSITIVE LOGITS
    _MANAGER
    0.07
     interchange
    0.07
     partners
    0.07
    frage
    0.07
     uncovered
    0.07
    .getUsername
    0.07
    )↵
    0.07
     Courtesy
    0.06
     максималь
    0.06
     refurb
    0.06
    Act Density 0.011%

    No Known Activations