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

    Neuronpedia

    INDEX
    Explanations

    preposition or conjunction following

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /
    -0.09
    .SuspendLayout
    -0.09
    °ëĭ¤
    -0.09
    IJëĭ¤
    -0.09
     till
    -0.08
    ãĢĤwww
    -0.08
    ined
    -0.08
    aro
    -0.08
     :|:
    -0.08
     ìŀĪìĹĪëĭ¤
    -0.08
    POSITIVE LOGITS
    ãģĹãģ¦ãģĬãĤĬ
    0.11
    Â
    0.10
    ãģĬãĤĬ
    0.10
     throughout
    0.09
    EMPLARY
    0.09
    åĩºãģĹ
    0.09
    ï¼Į並
    0.08
     [],
    0.08
    ','',
    0.08
    \',
    0.08
    Act Density 0.105%

    No Known Activations