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

    Neuronpedia

    INDEX
    Explanations

    content related to personal experiences and reflections

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

    Follows a period

    np_acts-logits-general · gemini-2.0-flash

    cause or situation during

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    むしろ
    -0.76
     Apalagi
    -0.75
    reszcie
    -0.67
     definitiva
    -0.66
     jopa
    -0.65
     sogar
    -0.65
     zelfs
    -0.65
     definitivo
    -0.64
    何より
    -0.64
    Удачи
    -0.63
    POSITIVE LOGITS
    Naturally
    0.77
     during
    0.76
     Naturally
    0.75
     During
    0.71
    évaluateur
    0.71
    during
    0.70
     prior
    0.68
    During
    0.68
     DURING
    0.65
     due
    0.62
    Act Density 0.421%

    No Known Activations