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

    Neuronpedia

    INDEX
    Explanations

    all

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _side
    -0.08
    _index
    -0.07
    ologists
    -0.07
     gatherings
    -0.07
     Edgar
    -0.07
     Tucker
    -0.07
    -0.07
    estado
    -0.06
    (step
    -0.06
    edir
    -0.06
    POSITIVE LOGITS
     overwhel
    0.07
     контр
    0.06
    佛
    0.06
     �
    0.06
     플
    0.06
     बच
    0.06
    ังคม
    0.06
     Child
    0.06
     }:
    0.06
     κ
    0.06
    Act Density 0.012%

    No Known Activations