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

    Neuronpedia

    INDEX
    Explanations

    jaws

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .§
    -0.07
    -fr
    -0.07
    Inc
    -0.06
    งแรก
    -0.06
     слыш
    -0.06
    G
    -0.06
     Dank
    -0.06
     boiling
    -0.06
    -layer
    -0.06
    _quantity
    -0.06
    POSITIVE LOGITS
    PAD
    0.06
    esion
    0.06
    oldown
    0.06
    níka
    0.06
    ighest
    0.06
    oley
    0.06
    ARSER
    0.06
     фін
    0.06
    βολή
    0.06
    ondere
    0.06
    Act Density 0.044%

    No Known Activations