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

    Neuronpedia

    INDEX
    Explanations

    reduction or temper

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     youthful
    -0.08
    ическом
    -0.08
     đỏ
    -0.07
     Vineyard
    -0.07
     körper
    -0.07
    יינו
    -0.07
    inian
    -0.07
     beleid
    -0.07
    红
    -0.07
     shook
    -0.07
    POSITIVE LOGITS
     druh
    0.08
     -*-↵↵
    0.08
     €.
    0.08
     �
    0.08
     znamen
    0.08
     ***↵
    0.07
    -thirds
    0.07
    ----------
    0.07
     ------------
    0.07
     استعمال
    0.07
    Act Density 0.001%

    No Known Activations