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

    Neuronpedia

    INDEX
    Explanations

    your prompt request

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Interviews
    0.49
     наши
    0.46
     usually
    0.41
     обеща
    0.41
     debates
    0.41
    Usually
    0.41
    Discuss
    0.40
     обычно
    0.40
     দেবেন
    0.40
    usually
    0.40
    POSITIVE LOGITS
     request
    0.56
     suggestion
    0.50
     misguided
    0.46
     message
    0.45
     phrasing
    0.43
     analogy
    0.43
     senaste
    0.43
     statement
    0.42
     reconsideration
    0.42
     posljed
    0.42
    Act Density 0.016%

    No Known Activations