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

    Neuronpedia

    INDEX
    Explanations

    2000s years

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ुगत
    -0.06
     вы
    -0.06
    _one
    -0.06
    .features
    -0.06
     attent
    -0.05
    chez
    -0.05
    (Employee
    -0.05
     essays
    -0.05
     kep
    -0.05
    らの
    -0.05
    POSITIVE LOGITS
    .";
    0.07
     preload
    0.07
     Obtain
    0.07
     spiked
    0.07
     builtin
    0.07
    ()↵↵
    0.07
    LAB
    0.06
     freeway
    0.06
     Lad
    0.06
    _SCANCODE
    0.06
    Act Density 0.035%

    No Known Activations