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

    Neuronpedia

    INDEX
    Explanations

    early stage or testing phases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     waktu
    0.71
     time
    0.71
     itu
    0.69
    </h3>
    0.66
    </b>
    0.65
     tyme
    0.64
     thief
    0.63
    </h2>
    0.61
     tijd
    0.60
     choral
    0.60
    POSITIVE LOGITS
     or
    0.81
     مركز
    0.75
    ab
    0.74
    0
    0.72
     Experimental
    0.71
     كم
    0.70
    Experimental
    0.70
    Cd
    0.70
    ors
    0.70
    ES
    0.70
    Act Density 0.153%

    No Known Activations