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

    Neuronpedia

    INDEX
    Explanations

    terms related to experimental methodology and design

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

    block or blocked

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OGND
    -0.51
    httphttps
    -0.42
    __(/*!
    -0.41
    ↹
    -0.39
    帖最后由
    -0.39
     cref
    -0.39
     Dalai
    -0.39
     Vedas
    -0.38
    ± 
    -0.38
    )：
    -0.38
    POSITIVE LOGITS
     block
    0.93
     BLOCK
    0.89
     Block
    0.81
    block
    0.77
    bloc
    0.76
    BLOCK
    0.75
     blocks
    0.75
    Block
    0.74
     bloc
    0.74
    ブロック
    0.71
    Act Density 0.067%

    No Known Activations