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

    Neuronpedia

    INDEX
    Explanations

    recover

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ruh
    -0.06
     Planning
    -0.06
    cı
    -0.06
    VIN
    -0.06
     decomposition
    -0.06
    .Place
    -0.06
    λογ
    -0.06
     tumors
    -0.06
    сол
    -0.06
     مرک
    -0.06
    POSITIVE LOGITS
     salvage
    0.08
     maximizing
    0.07
     SES
    0.07
    ossil
    0.07
     nejlepší
    0.07
    评
    0.06
     mRecyclerView
    0.06
     restitution
    0.06
     responsibly
    0.06
    eligible
    0.06
    Act Density 0.008%

    No Known Activations