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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating increasing levels or measurements

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

    up to limit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    المكان
    -0.50
    anneer
    -0.43
    erba
    -0.40
    ohjel
    -0.39
    illigen
    -0.38
    instein
    -0.37
    Cast
    -0.36
     questi
    -0.35
    ellschaft
    -0.35
     extranjero
    -0.35
    POSITIVE LOGITS
     until
    1.18
     jusqu
    1.13
     till
    1.11
     sampai
    1.10
    Until
    1.09
    until
    1.08
     Until
    1.08
     hasta
    1.06
     עד
    1.05
     untill
    1.04
    Act Density 0.044%

    No Known Activations