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

    Neuronpedia

    INDEX
    Explanations

    statements about truth and reality

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

    "truth" and its variants

    np_acts-logits-general · gemini-2.0-flash

    truth is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kör
    -0.55
    তথ্যসূত্র
    -0.53
     Forest
    -0.53
     Ro
    -0.49
    Forest
    -0.46
     newBuilder
    -0.46
     K
    -0.45
     I
    -0.44
     U
    -0.44
    <eos>
    -0.44
    POSITIVE LOGITS
     truths
    1.14
     Truths
    1.10
     TRUTH
    1.06
     Truth
    1.06
     truth
    1.02
    truth
    0.97
    Truth
    0.95
     Efq
    0.90
    цездатний
    0.88
     Verdad
    0.86
    Act Density 0.194%

    No Known Activations