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

    Neuronpedia

    INDEX
    Explanations

    common

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     outsourcing
    -0.07
     Behind
    -0.06
     getDate
    -0.06
     Unsupported
    -0.06
     poop
    -0.06
     восп
    -0.06
    ався
    -0.06
     Armour
    -0.06
    Rent
    -0.06
    ूल
    -0.06
    POSITIVE LOGITS
    โช
    0.07
    features
    0.07
    =.
    0.06
     روان
    0.06
     дви
    0.06
    音
    0.06
    Blocking
    0.06
    ocom
    0.06
    illegal
    0.06
    (term
    0.06
    Act Density 0.004%

    No Known Activations