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

    Neuronpedia

    INDEX
    Explanations

    personal preferences

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    LING
    -0.07
    _META
    -0.07
    ;",↵
    -0.06
    soup
    -0.06
     incorporation
    -0.06
    GUID
    -0.06
    وج
    -0.06
    /mL
    -0.06
    _client
    -0.06
     proposal
    -0.06
    POSITIVE LOGITS
    cairo
    0.06
    -Za
    0.06
    eman
    0.06
    incinn
    0.06
    anchors
    0.06
    .None
    0.06
     szy
    0.06
     умень
    0.06
    Car
    0.06
     Lola
    0.06
    Act Density 0.092%

    No Known Activations