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

    Neuronpedia

    INDEX
    Explanations

    reporting speech or observation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     घ्या
    0.66
    ই
    0.65
    させた
    0.64
    来的
    0.64
     মধ্যেই
    0.61
    どのような
    0.61
     인해
    0.60
    來的
    0.59
    発生
    0.59
     সবই
    0.59
    POSITIVE LOGITS
     bluntly
    1.34
     angrily
    1.20
     jokingly
    1.13
     solemnly
    1.12
    。.
    1.12
     succinctly
    1.10
     aloud
    1.10
    .¹
    1.08
     goodbye
    1.08
     emphatically
    1.07
    Act Density 0.009%

    No Known Activations