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

    Neuronpedia

    INDEX
    Explanations

    HTML or XML tag-like structures and their attributes

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

    Code snippets and configuration parameters

    np_acts-logits-general · gemini-2.0-flash

    computer parameters and stats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     soft
    -0.56
     Booth
    -0.55
     romance
    -0.52
    stor
    -0.51
     soph
    -0.51
    AccessorTable
    -0.49
    lioni
    -0.49
     sof
    -0.48
    IContainer
    -0.48
    soph
    -0.47
    POSITIVE LOGITS
    0.96
     estekak
    0.65
     azy
    0.65
    principalColumn
    0.62
    \}\\
    0.61
     protoimpl
    0.61
    0.59
     Alamo
    0.59
     vreme
    0.55
    0.55
    Act Density 0.044%

    No Known Activations