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

    Neuronpedia

    INDEX
    Explanations

    operation, transcription

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     IUnary
    0.43
    孢
    0.39
    _${
    0.38
     Everyday
    0.37
    ིས་
    0.37
    RegisterClass
    0.37
     PRODUCT
    0.37
    岕
    0.37
     <*>
    0.36
    ก
    0.36
    POSITIVE LOGITS
    Transcript
    0.47
    Transcription
    0.46
     transcript
    0.41
    Capt
    0.40
     transcription
    0.39
    transcript
    0.39
    Narr
    0.39
     étape
    0.39
     மதி
    0.39
     dobbiamo
    0.38
    Act Density 0.000%

    No Known Activations