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

    Neuronpedia

    INDEX
    Explanations

    lem

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    媒体
    -0.08
    ول
    -0.06
    URRED
    -0.06
     culturally
    -0.06
     battling
    -0.06
    orre
    -0.06
    드립니다
    -0.06
    _addresses
    -0.06
     Har
    -0.06
    Call
    -0.06
    POSITIVE LOGITS
    .deepcopy
    0.07
    ouncy
    0.07
    chop
    0.07
     sleepy
    0.06
    _accept
    0.06
    .we
    0.06
    _ps
    0.06
     centerX
    0.06
     힘
    0.06
     vlastně
    0.06
    Act Density 0.001%

    No Known Activations