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

    Neuronpedia

    INDEX
    Explanations

    employment termination

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    zero
    -0.06
    らく
    -0.06
     miser
    -0.06
     indice
    -0.06
    (bounds
    -0.06
     boxer
    -0.06
     대
    -0.06
     plane
    -0.06
    culated
    -0.05
    طار
    -0.05
    POSITIVE LOGITS
     passé
    0.08
    塔
    0.07
    _decimal
    0.07
     medio
    0.07
     komt
    0.06
    _upgrade
    0.06
     κορ
    0.06
    (mt
    0.06
    .addHandler
    0.06
     kilomet
    0.06
    Act Density 0.014%

    No Known Activations