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

    Neuronpedia

    INDEX
    Explanations

    terms related to memory accesses and operations

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

    memory access operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     houſe
    -0.69
     ſche
    -0.66
     Houſe
    -0.64
     pleaſure
    -0.63
    HomeAsUpEnabled
    -0.61
     myſelf
    -0.59
     ſtate
    -0.59
     ſtand
    -0.57
     ſch
    -0.57
     ſta
    -0.56
    POSITIVE LOGITS
    Referenties
    0.43
     dokun
    0.42
    úsqueda
    0.41
     desnuda
    0.40
     bezoek
    0.40
     citazioni
    0.38
     strijd
    0.37
     Wiktionnaire
    0.36
     attempted
    0.36
     dibanding
    0.36
    Act Density 0.197%

    No Known Activations