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

    Neuronpedia

    INDEX
    Explanations

    narratives involving groups and relationships among characters

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

    past lives and times

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     queſta
    -0.99
     nakalista
    -0.94
     فريبيس
    -0.80
    [@BOS@]
    -0.79
     Efq
    -0.79
    <unused28>
    -0.79
    <unused68>
    -0.79
    <unused41>
    -0.79
    <unused3>
    -0.79
    <unused16>
    -0.79
    POSITIVE LOGITS
    ceğine
    0.34
     round
    0.31
     MonoBehaviour
    0.28
     Round
    0.28
    round
    0.26
     lived
    0.25
     was
    0.24
     battle
    0.24
     living
    0.24
    stoß
    0.23
    Act Density 0.024%

    No Known Activations