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

    Neuronpedia

    INDEX
    Explanations

    increases and decreases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     getActivity
    -0.07
    毫
    -0.06
     Column
    -0.06
     Jest
    -0.06
     Jensen
    -0.06
     trả
    -0.06
     kendisi
    -0.06
    Pred
    -0.06
     Favor
    -0.06
     Schema
    -0.06
    POSITIVE LOGITS
     undecided
    0.07
    mnop
    0.06
    orida
    0.06
     DEVELO
    0.06
    Shortcut
    0.06
    oldur
    0.06
    icator
    0.06
    luž
    0.06
     imagin
    0.06
    extras
    0.06
    Act Density 0.098%

    No Known Activations