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

    Neuronpedia

    INDEX
    Explanations

    Nonsense/repeated strings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    endregion
    -0.06
     Ş
    -0.06
     Utils
    -0.06
    Scene
    -0.06
     Wing
    -0.06
     czę
    -0.06
    Lang
    -0.06
    getField
    -0.06
     alo
    -0.06
    	version
    -0.06
    POSITIVE LOGITS
     detal
    0.08
    ιλ
    0.07
     babes
    0.07
    itical
    0.07
    istributions
    0.06
    -gradient
    0.06
     Nx
    0.06
    .playlist
    0.06
    -your
    0.06
     поз
    0.06
    Act Density 0.033%

    No Known Activations