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

    Neuronpedia

    INDEX
    Explanations

    just

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Shift
    -0.07
    Rank
    -0.07
     nhập
    -0.06
     Renewable
    -0.06
     shift
    -0.06
    Usage
    -0.06
    анны
    -0.06
    ranking
    -0.06
    VK
    -0.06
     poisoned
    -0.06
    POSITIVE LOGITS
     Scar
    0.07
     Xã
    0.07
     revis
    0.07
     farther
    0.07
     modulo
    0.07
     LEGO
    0.07
    /local
    0.07
    Information
    0.07
     mapDispatchToProps
    0.06
     ASUS
    0.06
    Act Density 0.151%

    No Known Activations