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

    Neuronpedia

    INDEX
    Explanations

    technical terms and numerical values related to computation or statistics

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

    Code or special characters

    np_acts-logits-general · gemini-2.0-flash

    interested in, response directed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UseVisualStyle
    -0.51
    GOTREF
    -0.50
    I
    -0.50
    BC
    -0.49
    B
    -0.47
    IsContent
    -0.47
     kimi
    -0.46
    ling
    -0.46
    ة
    -0.45
    R
    -0.45
    POSITIVE LOGITS
    ]<<"
    0.84
     ligiloj
    0.84
    Portale
    0.81
    ViewFeatures
    0.78
    \}\\
    0.78
     "'");
    0.77
    ")));
    0.76
    )");
    0.76
    >");
    0.75
     autorytatywna
    0.73
    Act Density 0.099%

    No Known Activations