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

    Neuronpedia

    INDEX
    Explanations

    path/filename construction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     〈
    0.40
    mineral
    0.39
     क्लोरीन
    0.39
    .);
    0.39
     („
    0.38
    ষিত
    0.38
     terpenes
    0.38
    initis
    0.37
    ruvic
    0.37
    axies
    0.37
    POSITIVE LOGITS
    }_
    0.62
     %>/
    0.59
    }/
    0.57
    ]_
    0.50
    concat
    0.50
    +'/
    0.49
    +"/
    0.48
    )}_
    0.48
    ]}/
    0.47
    }/{
    0.46
    Act Density 0.033%

    No Known Activations