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

    Neuronpedia

    INDEX
    Explanations

    put together

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    लग्न
    0.42
     gleichzeitig
    0.38
     ज्
    0.38
     perpendicularly
    0.37
     jednocześnie
    0.37
    eaa
    0.37
    Merr
    0.37
    របស់
    0.36
     கோயில
    0.36
    fertil
    0.36
    POSITIVE LOGITS
     together
    0.78
    together
    0.65
     Zusammen
    0.64
     Together
    0.63
     sammen
    0.61
     assembled
    0.59
     össze
    0.59
     cobbled
    0.59
     zusamm
    0.57
     compiled
    0.56
    Act Density 0.005%

    No Known Activations