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

    Neuronpedia

    INDEX
    Explanations

    commencement of events

    np_acts-logits-general · gemini-2.5-flash-lite

    end of turn start

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
        
    0.87
    '
    0.87
    ד
    0.87
    ۰
    0.87
     ascribe
    0.82
    (
    0.81
    0.80
    Iran
    0.77
                    
    0.77
    EM
    0.77
    POSITIVE LOGITS
     temprana
    0.82
    is
    0.82
    ца
    0.81
     Starts
    0.81
     Gén
    0.78
     Quelques
    0.78
    आती
    0.76
    to
    0.76
     Commencez
    0.76
    starts
    0.75
    Act Density 2.937%

    No Known Activations