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

    Neuronpedia

    INDEX
    Explanations

    references to specific programming or technical terms related to a particular system or methodology

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

    WZ, wx, or vz followed by specific context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    脚注の使い方
    -0.47
    heroku
    -0.46
     Johansson
    -0.45
     mostrarán
    -0.44
    UnusedPrivate
    -0.42
    はじめに
    -0.42
    mės
    -0.41
    JMenuBar
    -0.40
     Lapp
    -0.40
    ituary
    -0.39
    POSITIVE LOGITS
     vz
    1.90
     wz
    1.83
     Vz
    1.28
    Vz
    1.19
    vz
    1.14
    Wz
    0.99
    wz
    0.95
    VZ
    0.81
     воз
    0.75
     wsp
    0.74
    Act Density 0.004%

    No Known Activations