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

    Neuronpedia

    INDEX
    Explanations

    worthlessness

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Border
    -0.07
    社会
    -0.07
    Template
    -0.06
    rozen
    -0.06
     Bath
    -0.06
    _card
    -0.06
    ferred
    -0.06
    ék
    -0.06
     століття
    -0.06
     Lis
    -0.06
    POSITIVE LOGITS
     İngilizce
    0.07
     segreg
    0.07
     ebp
    0.06
    .fill
    0.06
     robert
    0.06
    coal
    0.06
     conditioned
    0.06
    .get
    0.06
    RES
    0.06
    .CV
    0.06
    Act Density 0.031%

    No Known Activations