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

    Neuronpedia

    INDEX
    Explanations

    la luz, elementary operations, cases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    |[
    0.44
    }}]{
    0.39
     idP
    0.38
     !}
    0.37
    лес
    0.36
    #}
    0.36
    দ্দা
    0.36
    legi
    0.36
     साप
    0.35
    ❾
    0.35
    POSITIVE LOGITS
    OP
    0.81
     OP
    0.74
     op
    0.51
     ओपी
    0.50
    Op
    0.50
     OPC
    0.49
    opic
    0.46
     Opal
    0.45
    Thread
    0.45
    op
    0.44
    Act Density 0.001%

    No Known Activations