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

    Neuronpedia

    INDEX
    Explanations

    locations, borders

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     transformative
    -0.06
     derivation
    -0.06
    uxe
    -0.06
     trajectory
    -0.06
    .spatial
    -0.06
     kiss
    -0.06
    Substring
    -0.06
    .jdesktop
    -0.06
    ITES
    -0.06
     trajectories
    -0.06
    POSITIVE LOGITS
    _def
    0.07
    hv
    0.07
    书
    0.07
    _news
    0.07
     čist
    0.06
     Investig
    0.06
     ра
    0.06
    ￣￣
    0.06
    chants
    0.06
     allies
    0.06
    Act Density 0.180%

    No Known Activations