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

    Neuronpedia

    INDEX
    Explanations

    phrases that inquire about methods or processes

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

    how to ask for instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Enllaços
    -0.42
    
    -0.38
     thine
    -0.38
     agate
    -0.37
    \\\\
    -0.36
     ANYTHING
    -0.35
     nonfiction
    -0.35
     federally
    -0.34
    ROIT
    -0.34
    中略
    -0.34
    POSITIVE LOGITS
     ModelExpression
    0.54
    fjspx
    0.53
    tagHelperRunner
    0.53
    EndContext
    0.52
    interopRequire
    0.52
     can
    0.51
     does
    0.50
     would
    0.48
     JpaRepository
    0.48
     convenable
    0.47
    Act Density 0.029%

    No Known Activations