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

    Neuronpedia

    INDEX
    Explanations

    function

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    plitude
    -0.06
     Litecoin
    -0.06
     holdings
    -0.06
     лим
    -0.06
    _GF
    -0.06
    ्वर
    -0.06
     Literature
    -0.06
    ीटर
    -0.06
     Rape
    -0.06
     bone
    -0.06
    POSITIVE LOGITS
     sacram
    0.07
    :<?
    0.07
    .CenterScreen
    0.07
    trained
    0.07
     rt
    0.06
     tussen
    0.06
    compress
    0.06
    (URL
    0.06
    ]<
    0.06
    ))/
    0.06
    Act Density 0.005%

    No Known Activations