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

    Neuronpedia

    INDEX
    Explanations

    spoken words and manner

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :
    0.94
    :\
    0.85
    ：
    0.84
    "):
    0.74
     মধ্যেই
    0.71
     controlled
    0.68
    '):
    0.67
    :</
    0.67
    ":
    0.66
    자와
    0.66
    POSITIVE LOGITS
     bluntly
    1.13
    voice
    1.09
    1.08
    。.
    1.06
    ätta
    1.04
     smiling
    1.02
    .$,
    1.01
    smiling
    0.99
    ,+
    0.99
    ,=
    0.97
    Act Density 0.022%

    No Known Activations