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

    Neuronpedia

    INDEX
    Explanations

    references to complex narratives and interpretations

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

    describing qualities of content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Caruso
    -0.44
    ↹
    -0.43
    ệu
    -0.43
     hospitals
    -0.42
    illing
    -0.42
     landing
    -0.42
     hate
    -0.41
     OUR
    -0.40
     cambi
    -0.40
    ituation
    -0.40
    POSITIVE LOGITS
    帖最后由
    0.61
    期刊论文
    0.51
    ApiModelProperty
    0.48
    awtextra
    0.46
     endforeach
    0.44
    httphttps
    0.43
    WaitGroup
    0.43
    ($__
    0.41
    ፩
    0.41
    intéress
    0.40
    Act Density 0.021%

    No Known Activations