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

    Neuronpedia

    INDEX
    Explanations

    references to names or naming conventions

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

    appearing after "Name:" or "name:"

    np_acts-logits-general · gemini-2.0-flash

    name:

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ]));
    -0.61
     /\.(
    -0.59
    laştır
    -0.56
    Tikang
    -0.54
    setVerticalGroup
    -0.53
    kheim
    -0.51
    HomeAsUpEnabled
    -0.51
    hobo
    -0.49
    permum
    -0.49
    ことなく
    -0.49
    POSITIVE LOGITS
    plate
    0.95
    plates
    0.87
    Surname
    0.77
    lessness
    0.69
    ake
    0.69
    akes
    0.69
    PLATES
    0.64
     sake
    0.63
     newName
    0.63
    PLATE
    0.61
    Act Density 0.152%

    No Known Activations