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

    Neuronpedia

    INDEX
    Explanations

    crafts and decorations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Cleveland
    0.44
    Cleveland
    0.43
     Ahu
    0.43
     flav
    0.41
     hydroxy
    0.40
     pract
    0.38
     practic
    0.38
     چک
    0.38
     carve
    0.37
    鏃
    0.37
    POSITIVE LOGITS
     Pena
    0.39
     wig
    0.38
    zeppelin
    0.37
     Moving
    0.37
     Closing
    0.37
     Craft
    0.36
    湾
    0.36
    pé
    0.35
    fü
    0.35
    بير
    0.34
    Act Density 0.003%

    No Known Activations