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

    Neuronpedia

    INDEX
    Explanations

    Programming variables

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     puedo
    -0.07
     recurrence
    -0.06
    lsa
    -0.06
     hunted
    -0.06
    MethodName
    -0.06
    Typ
    -0.06
     administered
    -0.06
     Youth
    -0.06
    .seek
    -0.06
     supplements
    -0.06
    POSITIVE LOGITS
    ��
    0.06
    asil
    0.06
     whale
    0.06
     подой
    0.06
    росто
    0.06
    ンプ
    0.06
    ubble
    0.06
     incess
    0.05
    cond
    0.05
     case
    0.05
    Act Density 0.016%

    No Known Activations