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

    Neuronpedia

    INDEX
    Explanations

    Aragorn, wears

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     é
    0.49
    <unused2148>
    0.49
     idag
    0.47
     vier
    0.47
     idiosyncratic
    0.46
     دقت
    0.46
     davran
    0.45
    akkhati
    0.45
     ál
    0.45
     melewati
    0.45
    POSITIVE LOGITS
    AP
    0.50
    Ctrl
    0.49
     customer
    0.46
    Finish
    0.46
    Control
    0.46
    HA
    0.46
    ap
    0.46
    People
    0.45
    Heat
    0.45
    Florida
    0.45
    Act Density 0.001%

    No Known Activations