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

    Neuronpedia

    INDEX
    Explanations

    specific entities and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ڑے
    0.53
    medieval
    0.52
    انوي
    0.50
    മാ
    0.49
    غذ
    0.49
    ীপ
    0.48
    NUCLEAR
    0.48
    ച
    0.48
    нача
    0.48
    <0xA3>
    0.47
    POSITIVE LOGITS
    -
    0.54
    6
    0.52
    3
    0.50
    :
    0.47
    er
    0.46
     முன்ப
    0.46
    rom
    0.46
     het
    0.46
     enda
    0.45
    ruiter
    0.45
    Act Density 0.001%

    No Known Activations