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

    Neuronpedia

    INDEX
    Explanations

    equality

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    泣
    -0.07
    (guild
    -0.06
     Radius
    -0.06
    「お
    -0.06
     mammals
    -0.06
    _IList
    -0.06
    prov
    -0.06
     explicit
    -0.06
     Gim
    -0.06
    <?
    -0.06
    POSITIVE LOGITS
    rich
    0.07
    Keys
    0.07
     hợp
    0.07
     kick
    0.07
     наприклад
    0.06
    culate
    0.06
    roti
    0.06
    Fetch
    0.06
    ールド
    0.06
    owards
    0.06
    Act Density 0.000%

    No Known Activations