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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing impactful actions or moments of achievement

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

    "hit" or "hits"

    np_acts-logits-general · gemini-2.0-flash

    hit and run

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     שוליים
    -0.66
    scope
    -0.51
    SearchTree
    -0.46
     Mo
    -0.46
    Biographie
    -0.45
    Và
    -0.45
    Και
    -0.44
    AUTHENT
    -0.44
     esboço
    -0.44
    🔹
    -0.44
    POSITIVE LOGITS
     hits
    1.25
     hitting
    1.23
     HIT
    1.21
     hit
    1.20
     Hit
    1.19
    Hit
    1.13
     Hits
    1.11
    HIT
    1.05
    hit
    1.05
    hits
    1.05
    Act Density 0.058%

    No Known Activations