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

    Neuronpedia

    INDEX
    Explanations

    words related to "prior" or "before" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    при and related prefixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uropa
    -0.60
    ESO
    -0.60
    olanda
    -0.60
     Babel
    -0.59
    stdc
    -0.59
    ſelves
    -0.59
    zeb
    -0.58
     PUBL
    -0.58
     Belf
    -0.57
     semantics
    -0.57
    POSITIVE LOGITS
     при
    0.81
    При
    0.75
     При
    0.74
     Przy
    0.74
    Przy
    0.70
     przy
    0.69
    при
    0.62
    przy
    0.62
     při
    0.54
     Při
    0.52
    Act Density 0.002%

    No Known Activations